# Context Lifecycle
Providing context to your agents is useful, but it's not enough. Context needs to be treated like code: created, tested, evaluated, distributed, and kept up to date as systems change.
Tessl is an **Agent enablement platform** that provides a complete lifecycle for agent context.
## The lifecycle stages
### Use
Install context from the registry or within your team.
* Browse the [Tessl Registry](https://tessl.io/registry), or ask your agent to search Tessl for public skills, documentation, and rules
* Search for context specific to your tech stack and workflows
* Install trusted, evaluated context with version control
* Access private workspace context shared across your team
**Why it matters**: Start with quality context instead of writing everything from scratch.
See: [Make your agents smarter with documentation](/use/make-your-agents-smarter-with-documentation.md) and [Enhance your workflow with skills](/use/enhance-your-workflow-with-skills.md)
### Create
Build skills, documentation, and rules that teach agents how to work with your systems.
* Write skills that encode step-by-step workflows and procedures
* Create documentation for internal APIs and proprietary libraries
* Define rules for coding standards, security policies, and team conventions
* Develop locally and iterate quickly
**Why it matters**: Capture your team's knowledge and best practices as reusable context.
See: [Creating skills](/create/creating-skills.md), [Creating documentation](/create/creating-documentation.md), [Creating tiles](/create/creating-tiles.md)
### Evaluate
Test that context actually improves agent behavior with measurable quality scores.
* Lint and review skills for structure and completeness
* Run evaluations to measure agent accuracy improvements
* View quality scores before deploying to your team
* Identify what needs improvement with detailed validation results
**Why it matters**: Know that your context works before rolling it out. Prevent regressions as systems change.
See: [Evaluating skills](/evaluate/evaluating-skills.md), [Evaluating documentation](/evaluate/evaluating-documentation.md)
### Distribute
Roll out context across repositories, teams, and agents automatically.
* Publish to the Tessl Registry for team or public access
* Distribute across multiple repositories with GitHub/GitLab integration
* Keep context version-matched to your code and dependencies
* Update once, deploy everywhere
**Why it matters**: Enforce context automatically across agents and repos. No manual copying or syncing.
See: [Distributing via registry](/distribute/distributing-via-registry.md), [Rollout to your repositories](/distribute/rollout-to-your-repositories.md)
## Why the lifecycle matters
Without a lifecycle, agent context becomes stale, untested, and inconsistent. Teams end up:
* Copying prompts between projects and hoping they stay current
* Maintaining duplicate guidance in multiple places
* Not knowing if context actually improves agent behavior
* Manually syncing updates across teams and tools
Tessl treats agent context as managed software with the same rigor you apply to your codebase. Context is versioned, evaluated, distributed, and kept up to date automatically.
## Getting started
1. **Use existing context**: Install skills and documentation from the [Tessl Registry](https://tessl.io/registry)
2. **Create your own**: Build custom skills and rules for your team's workflows
3. **Evaluate quality**: Test locally and review scores before deploying
4. **Distribute**: Roll out to your repositories and team automatically
See the [Quick start guide](/introduction-to-tessl/quickstart-skills-docs-rules.md) to begin.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.tessl.io/introduction-to-tessl/context-lifecycle.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.