AI Engineer conference talk, July 22, 2026. A pharma analytics pipeline that split signal detection, source localization, driver attribution and synthesis across separate agents produced individually correct but collectively incoherent output, because context was lost at each handoff. The ZS presenters rebuilt it around one reasoning agent and a domain knowledge graph used as a control plane, where every edge in the graph is a hypothesis the agent tests against real data. (Auto-generated captions do not reliably separate the two speakers, so claims here are attributed to both presenters jointly.)
In the News: August 12, 2026
A Thoughtworks study finds TDD inside the agent loop costs 3 to 8.5x the tokens with no consistent quality gain.
Morning edition
Machine-readable
Download Markdown
Story
TDD inside the agent loop doesn't pay for itself, a small controlled study finds
Böckeler had Sonnet 4.6 build the same small, medium and large greenfield tasks with and without TDD instructions, twice each across five batches, then had Opus 4.8 blind-judge the resulting code and tests without knowing which workflow…
Read story →
Story
A 10,000-line skill made a coding agent worse, and nobody noticed until it was measured
Nisi generated a 10,000-line skills library from WorkOS's documentation, with each skill hashed to its source section so it would only regenerate on a real doc change. Evals of that library took 68 minutes to run per pass, per the…
Read story →Why We Killed Our Multi-Agent Pipeline
The Tower Keeps Rising
lucumr.pocoo.org, July 13, 2026. Argues that coding agents remove the coordination friction, pull requests, code review, interface negotiation, that used to force a team's mental models of a shared system to stay synchronized, so "construction can continue after shared understanding has already collapsed."