Atlas plans before it edits by running 2 separate agents. The plan agent is read-only: it can read your repository and draft an approach, but it cannot write a file. When the plan is complete Atlas asks whether to switch to the build agent, and only then can anything be written. In 2026 that separation is what lets you argue with an approach before it costs you a diff.
Why planning is a separate agent, not a prompt
Asking a model to describe its plan first is 1 instruction it can ignore. Atlas instead runs planning in a read-only agent that has no write tool at all, so a plan cannot quietly become an edit halfway through a response.
The difference matters most on the changes you would most want to review. A large refactor described in prose can look reasonable and still touch the wrong files. When the planning agent is structurally unable to write, the review step is guaranteed rather than requested, and the model's compliance is not part of your safety story.
The handoff you approve
When a plan is finished Atlas asks 1 question: whether to switch to the build agent and start implementing. Answering no leaves your working tree exactly as it was, and the plan stays available to revise or discard.
This is the point where most of the value lands. Rejecting a plan costs nothing, because no file has been touched, and revising a plan is far cheaper than reviewing and reverting a set of edits that already exist. Teams that plan first tend to spend their review attention on the approach rather than on the diff.
Planning and permissions reinforce each other
Approving a plan does not approve its edits. Each file change still computes a unified diff and passes through the allow, ask, or deny permission check, so there are 2 independent gates between an idea and a written file.
Planning catches the wrong approach; diff review catches the wrong implementation of a right approach. They fail differently, which is why Atlas keeps both rather than treating an approved plan as blanket consent for whatever the build agent decides to do next.
Frequently asked questions
- Does Atlas plan before editing files?
- Yes. Atlas drafts a plan in a read-only plan agent that cannot write files, then asks before switching to a build agent to implement it.
- Can the plan agent change my code by accident?
- No. The plan agent has no write capability, so planning cannot modify your working tree regardless of what the model decides to do.
- What happens if I reject a plan?
- Nothing is written. Your working tree is unchanged and the plan can be revised or discarded.
- Does approving a plan approve all its edits?
- No. Every file edit still computes a unified diff and passes the allow, ask, or deny permission check before it is written.
Try Atlas in your terminal
The terminal-native AI coding agent. Free core, single binary.
Install AtlasRelated guides
Atlas for Pandas: Terminal-Native AI Coding in 2026
Atlas is a terminal-native AI coding agent for Pandas. Vectorize df.apply, fix chained assignment under Copy-on-Write, and pin DataFrames with assert_frame_equal.
Atlas with Gemma 3 27B Instruct on Amazon Bedrock: Flat Pricing, 202,752 Tokens (2026)
Gemma 3 27B Instruct in Atlas via Amazon Bedrock: $0.12 per Mtok input, $0.2 per Mtok output, a 202,752 token context, open weights, and an 8,192 token output cap.
Atlas with OpenAI o3-mini in 2026: Still Worth Pinning?
OpenAI o3-mini runs in Atlas at $1.10 per Mtok input and $4.40 per Mtok output on a 200K context, but o4-mini costs exactly the same and is newer. Here is the call.
Atlas with DeepSeek-R1 (local via Ollama): Visible Reasoning at Every Size in 2026
DeepSeek-R1 runs locally from 1.5B to 671B under one Ollama tag, with a 128K to 164K context, free self-hosted, or $1.35 / $5.40 per Mtok via Bedrock. Atlas setup.
Atlas with Ollama Cloud in 2026: Hosted Ollama Tags for a Terminal Coding Agent
How to run Atlas on Ollama Cloud in 2026: same local tags like qwen3-coder:480b on hosted GPUs, up to 1,048,576 tokens of context, no published per-token price.
Atlas with Gemma 4 31B (Ollama): the Flagship Gemma 4 Tag in 2026
Gemma 4 31B (Ollama) is the largest Gemma 4 tag: 20GB weights, a 256K tokens (262,144) context, Free (self-hosted), plus a 31b-coding-mtp-bf16 variant. Atlas setup.
Atlas for Phoenix in 2026
Atlas is a terminal-native AI coding agent for Phoenix in 2026. It reads contexts, LiveView modules, and Ecto changesets, then runs mix test behind a prompt.
Atlas with Phi-4 (local via Ollama): The 16K Context Tradeoff in 2026
Phi-4 (local via Ollama) drives Atlas at Free (self-hosted) pricing with a 16K tokens (16,384) window. Setup, the 14B reasoning case, and where it breaks.