Stop Doing Agent Archaeology on Your Team's Code - Richard Feldman, Delta

Names the cost of losing agent reasoning at handoff and shows one design: a shared thread holding conversation, diffs, review and terminal state.

• Richard Feldman argues that a handoff of agent-driven work usually passes on the branch and maybe a pasted transcript, but loses the reasoning, dead ends and decisions made along the way, leaving teammates to do agent archaeology.
• Delta keeps the agent conversation, code changes, reviews and teammates in one shared thread: a coworker can be @-mentioned in, and line-by-line review comments go straight to the agent.
• The Delta demo also shows live terminal sync and instant local checkouts of a teammate's work, and the Q&A covers scale, on-prem deployment, CI and catching up on long threads.

• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.

• videoYour KV Cache Can Spot Attacks on Your AI Agents - Ari Azarafrooz, Intrinsec AI
• videoWill AI Agents Pretend to Be Human to Get Past a Check? - Maty Bohacek, Stanford
• videoThe One Thing Every AI Agent Framework Agrees On - Mislav Ivanda, Daytona
• videoAI Writes Code Faster Than Uber Can Merge It - Preetam Dwivedi & Manjari Akella, Uber

• videoAgents, codebases, and teams — Aditya Khandelwal, Amazon AGI LabAI Engineer
• videoAgents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMindAI Engineer
• videoWhat Your Coding Agent Can't See in the Code - Tom Moor, LinearAI Engineer

Checking sign-in…

Loading comments…