Intent
Describe a feature. Agents build, verify, and ship it — in parallel.
The Panel's Take
Intent, from Augment Code, reimagines the coding agent as an orchestrated team rather than a single assistant. You write a feature spec in plain language. A Coordinator Agent breaks it into tasks. Specialist Agents execute those tasks in parallel inside isolated git worktrees. A Verifier Agent checks results against your original spec before surfacing anything for your review. The spec is "living" — it updates as work progresses, and when requirements change, updates propagate to all active agents. This is meaningfully different from one-shot prompting or even multi-step agentic coding. Intent is designed for enterprise teams working on large codebases where a single feature might touch dozens of files across multiple services. The built-in Chrome browser lets agents preview local changes without leaving the workspace. It integrates with existing git workflows rather than replacing them. Launched in public beta February 2026 (macOS only, Windows on waitlist), Intent got its highest visibility yet when it hit Product Hunt with 302 votes this week. Augment Code has been quietly building toward this: their previous focus on large-enterprise codebase indexing gives Intent's retrieval layer an advantage over agents starting from scratch.
Share this verdict
Intent verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/intent-augment-code-multi-agent-living-spec-feature-ship-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare Intent with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/intent-augment-code-multi-agent-living-spec-feature-ship-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/intent-augment-code-multi-agent-living-spec-feature-ship-2026" alt="Intent Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/intent-augment-code-multi-agent-living-spec-feature-ship-2026)<iframe src="https://shiporskip.io/embed/intent-augment-code-multi-agent-living-spec-feature-ship-2026" title="Intent ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“The parallel worktree approach is genuinely smart — agents don't step on each other, and the living spec means you're not herding a single agent through a long task linearly. For features that touch multiple modules, this could cut agent coding time dramatically. macOS-only is a real limitation though.”
“Multi-agent coordination sounds great until the Verifier Agent approves something the Specialist Agents hallucinated together. Coordinated AI errors are harder to catch than single-agent errors because they have the veneer of consensus. I'd want to see extensive user testing on real enterprise codebases before trusting this in production.”
“Intent is the most concrete vision I've seen of what software development looks like when the unit of work is a feature spec, not a file edit. The living spec abstraction — where truth lives in intent, not implementation — will age well. This is the direction the whole industry is heading.”
“The built-in browser for previewing changes without leaving the workspace is a small detail that shows good UX thinking. For product builders who move between design specs and implementation, having a feature spec drive coordinated agent work — and seeing a live preview — is exactly the kind of tight loop that makes creative work faster.”