The talk frames a software factoryAn autonomous software factory is a repeatable development system that coordinates agents, tools, checks and human review to turn specifications into verified software changes. as a workflow that moves work from issue triage toward production. Its first improvement loop has an agent inspect a triage agent's runs and human feedback, then propose revisions to the triage skillAn AI agent skill is a reusable package of instructions, resources, and tool guidance for performing a bounded kind of work.. The example keeps those changes in a pull request for human review, so an erroneous revision can be caught before the skill changes.
A second loop extracts reusable facts and outcomes from past runs into an agent-scoped memory storeAI agent memory is stored information that an agent can retrieve and use across steps, sessions, or changing contexts.. The example concerns recurring software issues: stored root-cause context can help a later run avoid rediscovering the same information. The speaker also describes versioning, source tracing and human review of memories.
Finally, the talk argues for assigning different model classes to different tasks instead of using one expensive model everywhere. It describes task-specific routing rulesAI model routing sends each request to a model chosen for that request's complexity, cost, speed, privacy, or other requirements. and an evaluation approach that compares models on a team's own workflowsWorkflow-specific AI evaluation tests systems using the tasks, tools, constraints, and outcomes of a real working process.. The evaluation and customer-facing routing capabilities are presented partly as current internal practice and partly as future work, not as a measured general performance result.
Watch on YouTube
