What Comes After AI Coding Assistants
summary
Background agents move code generation off laptops into the cloud and claim to free teams from manual initiation by combining ephemeral development environments with a coding harness that provisions tools, enforces secure sandboxing, and adds runtime governance and observability. The platform Ona runs fleets of agents and the summit contrasts IDE copilots with agentic workflows that persist state, trigger on events, and parallelize work; one implementation reports shipping 1,000 PRs/week. The hard problems called out are review triage, permissions, and scaling trust and governance.
AI-written summary · about
chapters (6)
- 0:00Welcome
- 1:48AI coding assistants' limits
- 5:42Background agents overview
- 8:11Local agents to factories
- 10:01Three pillars for agents
- 14:36Summit expectations
related talks
26mAI Agents as Your Co-Developer
27mAgentic Engineering: Working With AI, Not Just Using It
49mFrom autocomplete to agents: AI coding assistance state of play
24mMixing AI Coding in IDEs, CLIs, and Cloud
41mGoing beyond copilot with AI Agents
29mPairing with the machine: How AI Agents are rewriting the rules of software development
16mBeyond the IDE: The Future of Developing Software With Agents
33mThe Autonomous Enterprise