Before You Switch Models, Replay Your Own Call Shapes Against the Candidate for a Few Tokens
Change a model ID and the first production request is where a 400 shows up. Here is a small replay script that checks your own call shapes against a candidate model with max_tokens 16 before you switch.
Don't Hand Your Agent the Tool That Commits — Sorting Tools Into Advise, Prepare, and Commit
Before you wrap irreversible actions in an approval gate, decide which ones never belong in the tool list at all. A three-tier inventory, a rewritten tool definition, and a small script that flags commits hiding in your schema.
Canva × Claude in Practice — Saving Generated Candidates, Picking a design_type, Committing Edits
The parts of the Canva AI connector that actually trip people up in Claude: why generated designs are not saved yet, how to pick a design_type, why editing is a transaction, and what to check before exporting.
Rolling Out Agent Behavior Changes Gradually with Feature Flags
When an unattended agent changes its prompt or behavior all at once, quiet regressions hide until morning. Here is a design for assigning new behavior to only a fraction of runs, keeping a control group, and adding deterministic bucketing, canary comparison, and automatic rollback.
When the Previous Run Hasn't Finished and the Next One Starts: Leases and Fencing Tokens for Scheduled Agents
A scheduled agent that runs on a fixed clock can overtake itself and start twice. From the moment a naive lock breaks to leases, fencing tokens, and bounded catch-up — worked through with the implementation I actually run.
Working Between Claude Design and Claude Code — Splitting Diverge and Converge
Rough design in Claude Design, fine detail in Claude Code. Now that the two live close together in the desktop app, here is how to run them as a divide-of-labor between diverging and converging — bridges like Link Local code and Send to included.
An Anti-Corruption Layer for Claude API Models — Keeping Generation Changes Out of Your Business Logic
Hard-coding model strings into business logic means production breaks quietly every time a generation is retired. Here is an anti-corruption layer that separates logical roles from physical model IDs, with working TypeScript and Python, migration costs, and the judgment calls behind it.
Guard Your Agent's Destructive Operations with Pre- and Post-condition Contracts
A design for wrapping an autonomous agent's writes in deterministic pre- and post-condition checks. A contract gate stops the destructive operations that better prompts can never reliably prevent.
Two Personalities for Claude Code — A Morning and Afternoon Workflow That Separates Exploration from Implementation
Treating Claude Code as a different persona in the morning and afternoon stabilises design decisions. A solo developer's six-month run with two CLAUDE.md files, a switching script, and the failure modes I hit along the way.
Turning Claude Code Into a Design Sparring Partner
How to use Claude Code as a sparring partner for design decisions rather than a code generator. The questioning craft I have refined while running four sites and several apps as a solo developer.
Figma × Claude Code Integration Guide — Bridging Design and Code with MCP
Learn how to connect Figma and Claude Code via MCP server for bidirectional design-to-code workflows, from setup to practical techniques.