Coding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, Tessl
Agent adoption becomes a team-systems problem: improve shared context and harnesses, assign platform ownership, and measure fewer human interventions instead of individual prompt speed.
The talk frames adoption across team, platform, and organization. Teams improve shared context and harnesses; platform owners curate reusable skills, evals, guardrails, and identities; leadership gives those owners a mandate rather than relying on scattered experiments.
Move retrospectives from patching agent-written code toward fixing the system that produced it. Route well-scoped work to agents, track **human touches**, and make each harness or context improvement benefit the whole team through **shared registries** and clear ownership.
The talk frames adoption across team, platform, and organization. Teams improve shared context and harnesses; platform owners curate reusable skills, evals, guardrails, and identities; leadership gives those owners a mandate rather than relying on scattered experiments. Move retrospectives from patching agent-written code toward fixing the system that produced it. Route well-scoped work to agents, track **human touches**, and make each harness or context improvement benefit the whole team through **shared registries** and clear ownership. The proposed dark factory is closer to a dim factory: autonomy should vary with feature risk, auditing, and verifier quality. The talk offers organizational patterns, not evidence that every team can reduce staffing or safely automate every workflow.
This extends the shared-harness view from repository practice into an organizational operating model: platform owners need authority to curate skills, evals, identities, and guardrails, while teams improve the production system rather than repeatedly repairing its output. It also narrows autonomy more explicitly than the prior candidates by tying it to risk, auditing, verifier quality, and measured human intervention.