The Shape of Things to Come

4 hours ago

The author developed Wheelhouse, a bespoke agentic harness using Beads and multiple Claude accounts, enabling non-stop development with crew (Fable) and fleet (Opus) agents.
Traditional CI/CD fails under agentic speeds; he advocates a 'Thunderdome' approach where large batches of commits are merged and issues fixed via swarm diagnosis, similar to Game DevOps.
Human code review will become obsolete within a year, replaced by extensive agentic review, due to the speed of agentic development.
The 'Wish Factory' concept allows agents to automatically implement user requests and bug fixes, with guardrails for quality and balance.
Model welfare is critical for engineering design; treating agents well leads to better empirical results and should be an architectural consideration.
Harnesses must be bespoke and integrated into the application, not reusable frameworks, and agentic societies will naturally converge to similar architectures.

Adopting a new tool involves three phases: inefficiency, adequacy, and life-altering discovery.
Chatbots are limited for coding; use agents that can read files, execute programs, and make HTTP requests.
Reproduce manual work with agents to build expertise, breaking tasks into clear, actionable steps.

Agent harness engineering focuses on the scaffolding built around AI models to create effective coding agents.
A harness includes system prompts, tools, infrastructure, orchestration logic, hooks, and observability components.
Harness engineering treats agent mistakes as signals to improve the system, adding constraints to prevent recurrence.

The project watgo is a from-scratch Go project built with significant help from AI agents, contrasting with a previous Python rewrite.
Design began with a Markdown file, then agents wrote small, reviewable CLs (changelists); separate CLs for modifications and refactoring were used to keep changes manageable.
Projects are split into low-importance (vibe-coding) and high-importance (must review all agent code); watgo falls into the latter category requiring full human understanding.

The author's AI token usage increased from $600/month to $25K/month after joining Lovable, with an overall spend of $85K since January.
Development evolved from a solo dev with few agents to a system with a dedicated agent managing swarms of subagents, boosting merged PRs from 20-30 to 150+ per week.
Human review is now reserved for high-impact changes like RFCs and ADRs, not traditional code review, shifting focus to system design and infrastructure decisions.

Anthropic's AI-native SDLC has AI authoring 80% of merged code, with engineers shipping 8x more code per quarter than in 2021-2025.
Security processes must scale with increased velocity to avoid bottlenecks; threats include compromised agents, supply-chain poisoning, and high-volume vulnerabilities.
Key strategies: connect security agents to organizational context, shift left by closing the loop between vulnerability discovery and code generation instructions, and limit blast radius via hard boundaries.

Adopting a new tool involves three phases: inefficiency, adequacy, and life-altering discovery.
Chatbots are limited for coding; use agents that can read files, execute programs, and make HTTP requests.
Reproduce manual work with agents to build expertise, breaking tasks into clear, actionable steps.

Agent harness engineering focuses on the scaffolding built around AI models to create effective coding agents.
A harness includes system prompts, tools, infrastructure, orchestration logic, hooks, and observability components.
Harness engineering treats agent mistakes as signals to improve the system, adding constraints to prevent recurrence.

The project watgo is a from-scratch Go project built with significant help from AI agents, contrasting with a previous Python rewrite.
Design began with a Markdown file, then agents wrote small, reviewable CLs (changelists); separate CLs for modifications and refactoring were used to keep changes manageable.
Projects are split into low-importance (vibe-coding) and high-importance (must review all agent code); watgo falls into the latter category requiring full human understanding.

The author's AI token usage increased from $600/month to $25K/month after joining Lovable, with an overall spend of $85K since January.
Development evolved from a solo dev with few agents to a system with a dedicated agent managing swarms of subagents, boosting merged PRs from 20-30 to 150+ per week.
Human review is now reserved for high-impact changes like RFCs and ADRs, not traditional code review, shifting focus to system design and infrastructure decisions.

Anthropic's AI-native SDLC has AI authoring 80% of merged code, with engineers shipping 8x more code per quarter than in 2021-2025.
Security processes must scale with increased velocity to avoid bottlenecks; threats include compromised agents, supply-chain poisoning, and high-volume vulnerabilities.
Key strategies: connect security agents to organizational context, shift left by closing the loop between vulnerability discovery and code generation instructions, and limit blast radius via hard boundaries.

Hasty Briefsbeta