# How do I ship faster with Claude Code and Cursor?

## The short answer

- Marc Lou: Measure AI productivity by things shipped, not by how many agents you run
- Rob Hallam: Route Claude Code work: cheap scout reads, top model plans and builds, fresh reviewer diffs
- Tibo: Have the AI write an image prompt to mock up a feature before building it

## Playbooks

### [Measure AI productivity by things shipped, not by how many agents you run](https://vibedraft.app/builder-brains/marc-lou/measure-ai-productivity-by-things-shipped)

Marc Lou · Building · Video

He keeps a 'boring' single-threaded setup: code editor plus one AI chat, build one feature, release, move to the next, instead of background agent teams.

**When it applies:** AI-assisted solo dev

Source: [How I Work: $77K/Month Solopreneur](https://www.youtube.com/watch?v=D4fkiQfzw_I), 26 April 2026 on youtube.com

### [Route Claude Code work: cheap scout reads, top model plans and builds, fresh reviewer diffs](https://vibedraft.app/builder-brains/rob-hallam/route-claude-code-work)

Rob Hallam · Building · X posts

Per task: scout agent (Opus, low effort, read-only) explores; the top model plans (high effort) then implements (medium) only files in a 'Files touched' list and writes an audit; Opus reviews the diff in a fresh context with Blocking/Non-blocking/Verdict output. Agent files live in ~/.claude/agents/, orchestrated by CLAUDE.md.

**When it applies:** Claude Code users hitting weekly usage limits

Source: [Rob Hallam: output-optimized Fable stack for Claude Code (thread)](https://x.com/robj3d3/status/2072603182149386299), 2 July 2026 on x.com

### [Run Claude Code on an €8/month VPS reachable from your phone](https://vibedraft.app/builder-brains/rob-hallam/run-claude-code-on-an-8-month)

Rob Hallam · Operations · X posts

Hetzner VPS, secured with Tailscale and a firewall, SSH via Termius, Claude Code installed, then log in from the phone to ship from anywhere (inspired by levelsio).

**When it applies:** nomadic/solo builders

Source: [Rob Hallam: Claude Code on a Hetzner VPS from your phone](https://x.com/robj3d3/status/2080016874889474091), 22 July 2026 on x.com

### [Have the AI write an image prompt to mock up a feature before building it](https://vibedraft.app/builder-brains/tibo/have-the-ai-write-an-image)

Tibo · Building · Podcast

When an AI-written spec is hard to picture, ask it for an image-generation prompt of the feature's UI, render it (he used Gemini's image model), keep the parts you like; discard specs you dislike and re-prompt rather than edit them.

**When it applies:** AI-assisted building

Source: [How This Solo AI Founder Bootstrapped 5 Products to 1M+ / Month | Tibo Louis-Lucas](https://www.youtube.com/watch?v=0UnZnonMN9o), 26 April 2026 on youtube.com

### [Plan with the strongest model, execute with a faster one](https://vibedraft.app/builder-brains/rob-hallam/plan-with-the-strongest-model)

Rob Hallam · Building · X posts

In Claude Code use plan mode (Shift+Tab) with Opus as the strategist, then switch to Sonnet to execute the plan step by step, avoiding chaotic one-shot coding.

**When it applies:** Claude Code users

Source: [Rob Hallam: complete guide to Claude Code (thread)](https://x.com/robj3d3/status/1935466820959617479), 18 June 2025 on x.com

### [Track multi-phase coding progress in a markdown file and /clear between phases](https://vibedraft.app/builder-brains/rob-hallam/track-multi-phase-coding-progress)

Rob Hallam · Building · X posts

Split large tasks into phases, checkpoint progress to an .md file, run /clear, then start the next phase so context stays small.

**When it applies:** long agentic coding tasks

Source: [Rob Hallam: output-optimized Fable stack for Claude Code (thread)](https://x.com/robj3d3/status/2072603182149386299), 2 July 2026 on x.com

### [Keep markdown context files and point the AI back to them when it drifts](https://vibedraft.app/builder-brains/tibo/keep-markdown-context-files-and-point)

Tibo · Building · X posts

Maintain files for business context, user context, architectural decisions, constraints and known failure modes; when a long coding session starts contradicting earlier decisions ('context rot'), point the agent at the files instead of re-explaining.

**When it applies:** building with AI coding agents on long sessions

Source: [Tibo: AI made 99.9% of devs slower (X long post)](https://x.com/tibo_maker/status/2026276723872936386), 24 February 2026 on x.com

### [Write behavioural test scenarios outside the codebase as a holdout set for AI agents](https://vibedraft.app/builder-brains/tibo/write-behavioural-test-scenarios-outside)

Tibo · Building · X posts

Because an agent can 'teach to the test' if it sees unit tests, store end-to-end user-behaviour specs separately and only use them to judge whether the software actually works for a real user.

**When it applies:** AI-native development at level 3+ (agent writes most code)

Source: [Tibo: AI made 99.9% of devs slower (X long post)](https://x.com/tibo_maker/status/2026276723872936386), 24 February 2026 on x.com

### [Vibe-design websites with Paper MCP, Refero references and ui.sh skills](https://vibedraft.app/builder-brains/rob-hallam/vibe-design-websites-with-paper-mcp)

Rob Hallam · Building · X posts

His design workflow: Paper MCP (Figma for agents) to design, Refero for real-world references so it doesn't look AI-generated, ui.sh agent skills for polish.

**When it applies:** builders who can't design

Source: [Rob Hallam: I 100% vibedesign all my websites now](https://x.com/robj3d3/status/2086883206301925800), 10 August 2026 on x.com

## Founders who talk about it

- [Tibo](https://vibedraft.app/builder-brains/tibo)
- [Marc Lou](https://vibedraft.app/builder-brains/marc-lou)
- [Rob Hallam](https://vibedraft.app/builder-brains/rob-hallam)

## Related topics

- [How do I set up agents that do real work?](https://vibedraft.app/builder-brains/topics/agent-workflows)
- [What can I automate with AI as a solo founder?](https://vibedraft.app/builder-brains/topics/ai-automation)
- [How do I keep AI costs from eating my margin?](https://vibedraft.app/builder-brains/topics/ai-costs)
- [Will AI make my startup pointless?](https://vibedraft.app/builder-brains/topics/ai-platform-risk)
- [How do I build an AI product that isn't just a wrapper?](https://vibedraft.app/builder-brains/topics/ai-products)
- [How do I write prompts and context that work?](https://vibedraft.app/builder-brains/topics/context-engineering)

Updated 2026-11-07. [Web version](https://vibedraft.app/builder-brains/topics/coding-agents)

Advice cards are rewritten summaries with a link to the original. They are not the founder's words unless shown in quotation marks.
