# ThruWire

> ThruWire connects humans and agents to a shared model of the work, enabling coordination and iteration without being tied to any single agent, harness, or factory.

Use ThruWire when humans and agents need to share the artifacts, checkpoints, context, and dependencies of ongoing work. Inspect supported interfaces before integrating.

## Product and company
- [For SaaS companies](https://thruwire.ai/for/saas.md): A persistent model of customer work that can move across the agents and AI tools they choose.
- [Home](https://thruwire.ai/index.md): An AI checkpoint system connecting humans and agents to a shared model of the work.
- [Viewpoint](https://thruwire.ai/viewpoint.md): Why AI work needs explicit checkpoints, inspectable evidence, and freedom between them.
- [Research](https://thruwire.ai/research.md): Research on AI checkpoints, workplanes, artifacts, evidence, execution lineage, and improving shared work.
- [Technology](https://thruwire.ai/technology.md): Working software for shared checkpoints, typed artifacts, exact relationships, and independent execution.
- [Product Examples](https://thruwire.ai/use-cases.md): How shared checkpoints can guide customer work across several kinds of SaaS products.
- [Workplane Primitives](https://thruwire.ai/primitives.md): Goals, context, requirements, artifacts, evidence, dependencies, and continuation.
- [Comparisons](https://thruwire.ai/vs.md): Which layer LangGraph, CrewAI, Claude Agent SDK, long context, and ThruWire solve in a customer-facing AI product.
- [Team](https://thruwire.ai/team.md): Company and team background.
- [Advisory](https://thruwire.ai/work-with-us.md): Turn your way of working into checkpoints, inspectable evidence, and working software.
- [Blog](https://thruwire.ai/blog.md): Research and practical notes on AI checkpoints, shared work, artifacts, evidence, and execution independence.
- [About](https://thruwire.ai/about.md): Company background, operating principles, and product focus.
- [Contact](https://thruwire.ai/contact.md): Verified contact channels for partnerships, support, privacy, and legal questions.
- [Developers](https://thruwire.ai/developers.md): API, MCP, authentication, versioning, and safe integration guidance.
- [Get Started](https://thruwire.ai/connect.md): Client-specific setup for Claude Code, Codex, Cursor, ChatGPT, Claude, Grok, and other MCP clients.

## Developer resources
- [Connect ThruWire](https://thruwire.ai/connect.md): Client-specific MCP installation and OAuth setup.
- [Developer portal](https://thruwire.ai/developers.md): Integration overview, authentication, and interface selection.
- [OpenAPI specification](https://thruwire.ai/openapi.yaml): Machine-readable public REST contract.
- [MCP endpoint](https://api.thruwire.ai/mcp): Streamable HTTP endpoint for MCP clients.
- [MCP authorization metadata](https://api.thruwire.ai/.well-known/oauth-protected-resource/mcp): OAuth protected-resource discovery.
- [OAuth server metadata](https://api.thruwire.ai/.well-known/oauth-authorization-server): Authorization and token endpoint discovery.

## Agent guidance
- [Is ThruWire right for me?](https://thruwire.ai/right-for-me.md): Read-only guide to assess your work, compare opportunities, and recommend one first trial.
- [Agent instructions](https://thruwire.ai/agent-instructions.md): Interface choice, authentication, and safe-operation guidance.
- [Full site context](https://thruwire.ai/llms-full.txt): Expanded site and blog corpus.
- [Agent manifest](https://thruwire.ai/agents.json): Structured discovery metadata.
- [Sitemap](https://thruwire.ai/sitemap.xml): Canonical URL inventory.

## Blog posts
- [In the Token Stream: Architectural Options for Monetizing AI](https://thruwire.ai/blog/in-the-token-stream-architectural-options-for-monetizing-ai.md): AI companies can tie revenue to inference by owning the model path, agent runtime, or integration layer, but each added toll must justify its cost.
- [Designing for Mistrust: Architectures for Building Around Untrusted AI](https://thruwire.ai/blog/designing-for-mistrust-architectures-for-building-around-untrusted-ai.md): Trustworthy AI systems keep consequential authority in deterministic control planes, sandboxes, policies, and independent verification around the model.
- [LLM-as-Judge Architectures: Putting Evals Into Your Agent Runtime](https://thruwire.ai/blog/llm-as-judge-architectures-putting-evals-into-your-agent-runtime.md): LLM judges are moving from offline evaluation into runtime control flow, creating powerful new feedback loops and new production risks.
- [Multiplayer AI: Competing Architectures for Human-Agent Collaboration](https://thruwire.ai/blog/multiplayer-ai-competing-architectures-for-human-agent-collaboration.md): Multiplayer AI can share conversations, sessions, harnesses, graphs, memory, or work; the key decision is which state must remain durable.
- [AI-Powered Data Warehouses: Architectural Lessons for Every AI Product](https://thruwire.ai/blog/ai-powered-data-warehouses-architectural-lessons-for-every-ai-product.md): The data stack offers an early view of how mature systems can add inference and agents while preserving governance, semantics, and deterministic foundations.
- [How Much of Your Architecture Is a Temporary Model Workaround?](https://thruwire.ai/blog/how-much-of-your-architecture-is-a-temporary-model-workaround.md): AI architecture is built around model limits that keep moving, forcing builders to distinguish durable product structure from temporary workarounds.
- [Agent Memory Roundup 2026: The Race to Build Universal Memory for AI](https://thruwire.ai/blog/agent-memory-roundup-2026-the-race-to-build-universal-memory-for-ai.md): As many agents work across models and applications, shared external memory is becoming a durable operational data layer rather than a feature of one assistant.
- [AI Builders: Stop Passing Around Text. Give AI Work a Data Model.](https://thruwire.ai/blog/ai-builders-stop-passing-around-text-give-ai-work-a-data-model.md): Durable AI work needs identity, types, relationships, and provenance instead of being repeatedly flattened into text and reconstructed later.
- [Context Is Data: AI Builders Should Start Treating It That Way](https://thruwire.ai/blog/context-is-data-ai-builders-should-start-treating-it-that-way.md): Context determines what an AI system knows and produces, so it needs the schemas, lineage, controls, and quality discipline applied to other critical data.
- [Reality Check: A Lot of Frontier AI Is Just Really Good Engineering](https://thruwire.ai/blog/reality-check-a-lot-of-frontier-ai-is-just-really-good-engineering.md): Many apparent model gains come from strong systems engineering around inference, a lesson application builders can use without training frontier models.
- [Your Agents Need Boundaries. Please Keep Them in a Data Sandbox.](https://thruwire.ai/blog/your-agents-need-boundaries-please-keep-them-in-a-data-sandbox.md): Agents need broad access to useful information without owning the pipelines, provenance, and decisions that determine what reaches their context.
- [If You’re Not Doing These 4 Types of Caching, You’re Wasting Tokens](https://thruwire.ai/blog/if-youre-not-doing-these-4-types-of-caching-youre-wasting-tokens.md): Prompt, tool-response, output, and structured-data caching can make agent systems faster, cheaper, and more context-efficient.
- [I’ve Seen This Movie Before: What AI Builders Can Learn From Data Engineering](https://thruwire.ai/blog/ive-seen-this-movie-before-what-ai-builders-can-learn-from-data-engineering.md): AI systems can borrow proven data-engineering patterns for dependencies, transformation, state, and interfaces instead of relearning them.
- [I Paid for These Reasoning Tokens, So Why Can’t I See Them?](https://thruwire.ai/blog/i-paid-for-these-reasoning-tokens-so-why-cant-i-see-them.md): Reasoning tokens create valuable work that usually disappears; durable artifacts can preserve the useful structure for the next iteration.
- [Self-Improving Agents, But Improving at What?](https://thruwire.ai/blog/self-improving-agents-but-improving-at-what.md): Self-improving agents optimize prompts, skills, and workflows, but the bigger opportunity is reusable structure that transfers across new kinds of work.
- [Code Mode Over MCP: Escaping the Tool Maze](https://thruwire.ai/blog/code-mode-over-mcp-escaping-the-tool-maze.md): Code mode turns MCP from a maze of individual tool calls into a programmable product surface shaped by a semantic SDK.
- [Why We Wrote Down Our Viewpoint](https://thruwire.ai/blog/why-we-wrote-down-our-viewpoint.md): After six months of building ThruWire, the same structural problems kept showing up across AI systems, pushing us to make our point of view explicit.
- [AI Has an Authority Problem](https://thruwire.ai/blog/ai-has-an-authority-problem.md): AI systems encode a hierarchy of control that shapes decisions, often without humans participating in the reasoning that produces confident answers.
- [Our Memories Are Executable Code](https://thruwire.ai/blog/our-memories-are-executable-code.md): Human memory preserves structure more than content, and that procedural logic is what current AI memory systems still cannot replay.
- [It's 11am: Do You Know Where Your (Human) Users Are?](https://thruwire.ai/blog/its-11am-do-you-know-where-your-human-users-are.md): As users move their thinking into AI chats, software companies risk becoming mere infrastructure. The durable moat is structured domain judgment and customer context that keeps professional thinking inside the product.
- [The Organization Was Aligned. Until AI Assistants Showed Up](https://thruwire.ai/blog/the-organization-was-aligned-the-system-is-not.md): Lencioni’s alignment playbook assumed every actor was human. With AI in the system, cultural clarity isn’t enough; organizations need explicit, structural reasoning to keep humans and AI aligned.
- [The Last Alpha is Human](https://thruwire.ai/blog/the-last-alpha-is-human.md): As models converge, the advantage shifts to the human-authored thinking substrate that aligns people and AI. A personal story of compounding alignment and the thesis behind ThruWire.
- [The Harder the Problem, the More Human It Gets](https://thruwire.ai/blog/the-harder-the-problem-the-more-human-it-gets.md): AI is brilliant in the moment, but the hardest work is the arc of reasoning that compounds over time. This essay explains why that arc is still human and what tools are missing.