Augment Code

Augment Code – Developer AI for real work

4.6•10 reviews•

748 followers

Augment Code – Developer AI for real work

4.6•10 reviews•

748 followers

Visit website

AI Coding Agents

Experience the AI platform that truly understands your codebase. Our developer AI helps teams code faster, make smarter decisions, and unlock collective knowledge. Try free today.

This is the 3rd launch from Augment Code. View more

Intent

Launched this week

Describe a feature and AI agents build, verify, and ship it

Intent is a developer workspace built for agent-driven development. Define a feature as a spec, and a team of agents coordinates the work (from implementation to verification) inside an isolated workspace with built-in code, terminal, and git.

Free

Launch tags:Productivity•Developer Tools•Artificial Intelligence

Launch Team

HiBird — Smarter communication for growing businesses.

Smarter communication for growing businesses.

Promoted

Hunter

📌

Excited to hunt Intent by Augment Code today.

Intent is a developer workspace where agents coordinate and execute work end-to-end.

This isn’t a coding assistant. It’s an agent-driven development system.

Instead of prompting one agent at a time, you define a spec and a coordinator breaks it into tasks, delegating to specialists (implement, verify, debug, review) running in parallel.

This adds up to:
• Specs that stay alive as work progresses
• Built-in verification loops, not just code generation
• A full workspace (editor, terminal, git)

If you’ve been exploring agentic dev but didn’t want to build the orchestration layer yourself , this is definitely worth a look.

Report

3d ago

Product Hunt

Isolation and parallelism sound great until you hit merge conflicts and cross-service coupling. How does Intent structure workspaces/branches (e.g., via worktrees), handle dependency ordering between agent tasks, and reconcile changes into a clean PR without a human acting as the traffic cop?

Report

19h ago

Maker

@curiouskitty Thanks for your question, it’s a good one.
Under the hood, Intent gives each task its own workspace backed by a git worktree + branch, so agents get an isolated checkout but share a single .git history for cheap branching and instant sync. The Coordinator turns your spec into a plan with explicit task dependencies, then runs specialist agents in waves: independent tasks in parallel, dependent ones after predecessors land, all staying aligned via a living spec that updates as work is done. On the back end, Intent has full git workflow built in (branching, commits, PRs, merge) plus auto-rebase/conflict surfacing, so you can stack or fan out branches without becoming the human traffic cop, you just review grouped changes per task/agent and ship.

Report

18h ago

Otto Radio

Maker

Wrote up a post on how our teams collaborate within Intent. We've been able to effectively eliminate the designer/developer handoff. More details on the process, screenshots, etc: https://lukew.com/ff/entry.asp?2148

Report

10h ago

Is there some form of hierarchy between the agents like in a real work scenario? Curious how they value each others opinions while working towards a shared goal

Report

11h ago

Maker

@tanner_beetge Yes. In Intent, agents are usually hierarchical, not a flat swarm:

A controller agent acts like a tech lead: it understands the main goal, breaks it into subtasks, runs specialist agents, and decides what to accept/merge.
Specialist agents do focused work (code, tests, analysis) and report back, they don’t “vote,” their outputs are checked against the shared spec + workspace + tests/CI, and the controller, the verifier agent (plus the human) has final say.

So they “value” each other’s work through this structure and verification, not by arguing as equal peers.

Report

11h ago

This sounds cool, tell me, how I can trust on quality of this agent for work?

Report

24h ago

Maker

@avinashvagh1 Totally fair question. A few concrete reasons teams trust Intent here:

It runs on Augment Code, which is SOC 2 Type II and ISO/IEC 42001 certified, with public security docs (no NDA needed).
Your code is never used for training, and the architecture is non-extractable with a Proof-of-Possession API, so it can’t exfiltrate code or leak across tenants.
You keep control via CMEK, encryption in transit/at rest, and continuous third-party pen-testing.
On quality: Intent is spec-first, with a coordinator + specialist agents + verifier that work in isolated git worktrees, so every change shows up as normal diffs you can review like any PR.

Public refs if you want to dig deeper: Trust Center trust.augmentcode.com and Security & Privacy augmentcode.com/security .

Report

17h ago

minimalist phone: creating folders

This is a complex thing. Who is the main target audience?

Report

16h ago

Maker

@busmark_w_nika The main target audience for Intent is senior, power-user developers, company with very large codebase and engineering teams who are actively using or motivated to adopt multiple AI coding agents, and who feel the pain of juggling terminals, IDEs, repos, and prompts to ship production code.

In practice, this skews toward ICs and tech leads at high-caliber software companies who want a serious, orchestrated agent workspace.

Report

14h ago

Jinna.ai

Congrats on the launch! Wondering what’s its integration capabilities with many common SDLC software, because building in isolation is great until you need to do some real work.

Report

15h ago

Maker

@nikitaeverywhere Intent doesn’t try to replace your SDLC stack, it plugs into it and gives you a unified workspace on top:

Git-native workspaces: Every Intent project runs in an isolated git worktree with full git workflow support (branches, commits, PRs, merge flow). You go from prompt → commit → PR → merged without leaving Intent.
You can connect all your MCPs in these workspaces just like you would in an IDE
Bring-your-own agents & tools: Intent works with multiple agent providers (Claude Code, Codex, OpenCode, Augment’s own agents), so it can sit alongside existing IDEs and CI/CD instead of locking you in.
Workspace, not a toy sandbox: Because it’s built around git and a real terminal, the code, tests, and scripts agents run in Intent are the same ones your SDLC uses no “demo-only” environment.

Net: Intent is designed for “real work” in production repos, integrating with your existing git/PR-centric SDLC rather than a sealed-off playground.

Report

14h ago

1 2 3

Previous Augment Code Launches

Augment AgentAI pair programmer that understands your codebase

Launched on April 14th, 2025

Augment CodeCoding Assistant with full codebase awareness

Launched on February 27th, 2025

Forum Threads

p/augment-code

•

3d ago

Intent by Augment Code. Is spec-driven multi-agent development the next step after the IDE?

Augment Code has been quietly building enterprise-grade coding tools for large engineering teams, and they launched Intent. heir answer to what comes after the IDE.

According to their announcement:

"The bottleneck has moved. The problem isn't typing code. It's tracking which agent is doing what, which spec is current, and which changes are actually ready to review."

View all

@nikitaeverywhere Intent doesn’t try to replace your SDLC stack, it plugs into it and gives you a unified workspace on top:

Git-native workspaces: Every Intent project runs in an isolated git worktree with full git workflow support (branches, commits, PRs, merge flow). You go from prompt → commit → PR → merged without leaving Intent.
You can connect all your MCPs in these workspaces just like you would in an IDE
Bring-your-own agents & tools: Intent works with multiple agent providers (Claude Code, Codex, OpenCode, Augment’s own agents), so it can sit alongside existing IDEs and CI/CD instead of locking you in.
Workspace, not a toy sandbox: Because it’s built around git and a real terminal, the code, tests, and scripts agents run in Intent are the same ones your SDLC uses no “demo-only” environment.

Net: Intent is designed for “real work” in production repos, integrating with your existing git/PR-centric SDLC rather than a sealed-off playground.