Technology / Anthropic Claude

Anthropic Claude, used where it earns its place

Claude is Anthropic's model family — Opus, Sonnet, and Haiku. We reach for it when an agent needs strong tool use, adaptive reasoning, and a million tokens of context. We never claim it's the only answer.

  • Tool use & agentic loops
  • Adaptive thinking + effort
  • 1M-token context window
  • Vendor-honest, no lock-in
1M
token context window on the Opus and Sonnet tiers
3
tiers: Opus, Sonnet, Haiku — matched per task
~0.1x
input cost on a prompt-cache read vs. a cold call
200+
tools an agent can carry with tool search
// what we actually use

The capabilities we lean on

Not a feature tour — these are the parts of Claude that change how an agent is built.

// how it fits the architecture

Where Claude sits in an agent

The model is one component behind a clean interface — not the architecture itself.

01

Reason

Claude plans the next step with adaptive thinking, weighing tool results and conversation state.

02

Act

It emits typed tool calls; our harness executes them against your systems, with gates on anything risky.

03

Observe

Tool results, errors, and stop reasons flow back; context editing and compaction keep the window lean.

04

Govern

Every call is logged with model, tokens, and decision lineage — the same audit trail regardless of which model ran.

// vendor-honest by design

A model choice, not a dependency

Every Automatic.co agent talks to a model through an interface we own. Claude lives behind that interface alongside OpenAI and open-source models. Switching a route from Opus to GPT or to a self-hosted model is a config change, not a rebuild.

That's deliberate. Model leadership moves quarter to quarter, pricing shifts, and some data can't leave your perimeter at all. We pick the model per workload on the merits — and we'll tell you when Claude isn't the right call.

  • Route per workload, swap by config
  • Run on Anthropic API, Bedrock, or Vertex
  • Pair with private/on-prem models where required

When we reach for Claude vs. when we don't

A working heuristic, not a rule. We validate per engagement.

Reach for ClaudeReach for something else
Task shapeMulti-step reasoning, heavy tool useHigh-volume classification or extraction
ContextWhole codebase / document set in viewShort, bounded prompts
Data residencyAPI, Bedrock, or Vertex is acceptableMust stay fully on-prem / air-gapped
Cost profileQuality justifies the per-token rateCheapest token-per-task wins outright

Frequently asked questions

Are you locked into Anthropic?

No. Claude is one model family we reach for, not a dependency. Our agents route to a model behind an interface, so we run Claude where its reasoning and long context earn it, and swap in OpenAI or an open model where those fit better.

Why Claude specifically?

Three reasons most often: strong multi-step tool use, adaptive thinking that scales reasoning to the task, and a 1M-token context window that lets an agent hold a whole codebase or document set in view. We pick it on the merits per workload, not by default.

Where does our data go?

Wherever the engagement requires. We can run Claude through Anthropic's API, through Amazon Bedrock or Google Vertex inside your cloud, or pair it with private/on-prem models for the parts that can't leave your perimeter.

How do you control cost and latency on Claude?

Prompt caching on the stable prefix, an effort setting tuned per route, streaming for long outputs, and the cheaper Haiku tier for sub-tasks. We measure tokens per workflow rather than guessing.

Bring the workflow. We'll pick the right model.

One working session to see whether Claude — or something else — is the right engine for your agent, and how it fits the rest of the stack.