Platforms We Deploy

    Claude AgentsProduction agents with permissions you control

    Pyra designs, deploys, and manages Claude agents for GTM, sales, marketing, and operations teams. According to Anthropic's documentation, the Claude Agent SDK puts the agent loop that powers Claude Code into your own application, and Claude Managed Agents runs long-running, asynchronous agents on Anthropic-hosted infrastructure.We turn that into scoped, permissioned workflows your team can approve — starting small and expanding only what proves out.

    Independent implementation partner: Claude, the Claude Agent SDK, and Claude Managed Agents are products of Anthropic. Pyra is not affiliated with, sponsored by, or endorsed by Anthropic — we design, deploy, and manage agent workflows on the platform for our clients. Platform facts verified August 18, 2026.
    Permission gates
    Tools approved, not assumed
    Start small
    Read-and-prepare first
    Data boundaries
    Designed per workflow
    Audit trails
    Actions logged & reviewed
    Who this is for

    Teams that need agents in production, not demos

    GTM & RevOps Leaders

    Want an agent wired into the GTM stack over MCP that owns a repeatable outcome — research, prep, and drafts — with permission rules you control.

    Sales & Marketing Teams

    Need account research, meeting prep, and drafted outreach produced in the background and left for review — nothing sends without sign-off.

    Operations Leaders

    Want long-running, multi-step workflows that survive pauses and resume cleanly, with data boundaries designed per workflow and audit trails throughout.

    What we deploy it for

    Four workflows we build on Claude

    Every workflow below is grounded in documented platform capabilities and configured with permission rules and human review. Pyra sells the implementation and management service.

    1) GTM: Account research & prep
    An agent connected to your stack over MCP that owns read-and-prepare work and leaves results for review.
    • Research accounts using web search and MCP-connected sources
    • Assemble briefs and account context into reviewable outputs
    • Permission rules keep write-actions behind approval
    • Human review before any downstream action
    2) Sales: Research to drafted outreach
    A pipeline that turns a prospect list into researched accounts and drafted outreach in your voice.
    • Pull prospect and account data from MCP-connected tools
    • Research and rank accounts against your criteria
    • Draft outreach and follow-ups in your team's voice
    • Leave drafts to approve — nothing sends without sign-off
    3) Operations: Long-running background work
    Built on Claude Managed Agents: asynchronous, stateful workflows that run without your team babysitting them.
    • Long-running sessions that pause and resume cleanly
    • Steer or interrupt the agent mid-execution
    • Cloud sandbox — or self-hosted sandbox on your infrastructure
    • Full event history for audit and review
    4) Custom: Agent SDK builds in your product
    For agents inside your own application, we build with the Agent SDK in Python or TypeScript.
    • The agent loop that powers Claude Code, in your own process
    • Built-in tools: files, commands, and web search
    • Hooks and subagents for structured, supervised workflows
    • Permission controls for which tools run automatically
    Why Claude

    What the platform actually does

    The following facts are drawn from Anthropic's documentation, verified August 18, 2026. Where a claim is made by the vendor, we attribute it as such.

    Agent SDK: Claude Code as a library

    Per Anthropic's documentation, the Agent SDK provides the same tools, agent loop, and context management that power Claude Code, programmable in Python and TypeScript — with built-in tools, hooks, subagents, sessions that resume or fork, and skills and memory.

    Permissions and MCP, org-wide

    Anthropic's documentation describes permission controls over which tools run automatically and which need approval, and MCP for connecting external tools and data. In June 2026, Anthropic added enterprise-managed authorization so admins can centrally authorize MCP connectors for their organization through their identity provider.

    Managed Agents: hosted, long-running

    Per Anthropic, Claude Managed Agents is a hosted REST API where Anthropic runs the agent and its sandbox — built for long-running and asynchronous work, with streaming events, mid-execution steering and interrupts, and a choice of cloud sandbox or self-hosted sandbox on your own infrastructure.

    A data-retention nuance

    Anthropic's documentation states Managed Agents is stateful by design — conversation history, sandbox state, and outputs are stored server-side — and is not currently eligible for Zero Data Retention. Pyra's deployment work includes designing data boundaries around this: what enters a session, when to use a self-hosted sandbox, and when to build on the Agent SDK in your own infrastructure instead.

    How Pyra deploys it

    Scope, integrate, then manage

    1. Scope & pilot

    We pick one workflow with a clear result, choose the right surface — Agent SDK in your infrastructure or Managed Agents — and start with read-and-prepare work.

    2. Integrate & configure

    We connect your tools over MCP, set permission rules for which tools run automatically and which need approval, and design data boundaries around what each session can reach.

    3. Manage & iterate

    We monitor, tune, and expand — widening permissions or adding workflows only once results hold up in review, with audit trails throughout.

    FAQ

    Common questions about our Claude deployments

    Is Pyra affiliated with Anthropic?

    No. Pyra is an independent implementation partner. We are not affiliated with, sponsored by, or endorsed by Anthropic. We design, deploy, and manage Claude agent workflows for our clients. Claude, the Claude Agent SDK, and Claude Managed Agents are products of Anthropic.

    Agent SDK or Managed Agents — which do you deploy?

    Both, depending on the workflow. Per Anthropic's documentation, the Agent SDK is a Python and TypeScript library that runs the same agent loop, tools, and context management that power Claude Code — inside your own process and infrastructure. Claude Managed Agents is a separate hosted product: Anthropic runs the agent and the sandbox behind a REST API, built for long-running and asynchronous work, with the option of a self-hosted sandbox on your own infrastructure. We match the surface to your data requirements and the shape of the workflow.

    Where does agent data live with Managed Agents?

    Per Anthropic's documentation, Claude Managed Agents is stateful by design: sessions are long-running, resume after pauses, and conversation history, sandbox state, and outputs are stored server-side. Anthropic's documentation also states that Managed Agents is not currently eligible for Zero Data Retention. Because of this, our deployment work includes designing data boundaries: choosing what enters a session, using a self-hosted sandbox where requirements call for it, or building on the Agent SDK in your own infrastructure instead.

    What's the fastest way to start?

    Start Free to scope one repeatable workflow with a clear result. From there we build the agent, connect your tools over MCP, set permission rules for which tools run automatically and which need approval, and pilot before expanding — with monitoring and audit trails throughout.

    Next step

    Put a Claude agent to work on one real workflow

    Start Free to scope a single read-and-prepare workflow with a clear result. Then Pyra builds the agent, connects your tools over MCP, sets permission rules and data boundaries, and manages the deployment as it expands. Independent implementation partner — not affiliated with Anthropic.