Features & Improvements
- AgentMark init
- Updated examples in CLI init
- Rebrand Puzzlet -> AgentMark
- CLI: “run-prompt” for dataset + single props
- Webhook Helpers
- Alerts enhancements
- Google/GitHub auth
- Dataset runs directly via prompts
- Vercel v4 webhook helper
- Streaming to the platform
- Commit History + Rollbacks
Bug Fixes
- Ollama fix on init
JSONL Datasets
Datasets are now supported with JSONL files. This allows you to test your large datasets in bulk against, and supports streaming.Read DocsEvals & Scoring
We rolled out our initial evals support. Evals allow you to evaluate your prompts against a set of data, and get a score. More to come here soon.Read DocsOther
- Consolidating prompts, evals, and datasets into single “files”
- Officially rolled out alerts
- Some CLI improvements
- Minor bug fixes
Sessions
Sessions provide a way to group related traces together, making it easier to monitor and debug complex workflows in your LLM applications. By organizing traces into sessions, you can track the entire lifecycle of a user interaction or a multi-step process.Read DocsAlerts
Now, you can get notified when your application is experiencing increases errors, latency, or costs. Configure alerts to notify you via slack, or a webhook.Read DocsTraces UI Improvements
Traces now have a more user-friendly UI, with a focus on providing important information at a glance.Onboarding Improvements
We’ve improved our onboarding. Now, you can see your dashboard without having to sync your repo first. We also support modular onboarding, so you can skip steps you don’t need.2025-02-18
Add Trace Examples to Datasets, Load Trace in Prompt, Re-indexing, App UI Improvments, bug fixes
Adding Examples to Datasets
You can now add production trace data to your datasets with a single click.Read DocsAdding Examples to Prompts
You can now add production trace examples to your prompts. This allows you to iterate/test against your prompts with real data.Read DocsRe-indexing
You can now re-index your prompts, and datasets. This allows you to perform a fresh pull on the content from your synced repository.App UI Improvements
You can now view your easily app’s repo configuration, including repo names, branch, and more.Type Safety
AgentMark aims to provide developers with the best developer experience possible. As part of this, we’ve just added type safety to our platform.- Types can now be generated via our CLI
- Fetching prompts from our CDN or AgentMark are now type-safe
- Prompts now support run/compile/deserialize functions
Read more about Type SafetyDatasets
Datasets now allow you to test your prompts in bulk against a large set of data.- Run your datasets in bulk against your prompts
- View previous runs, with inputs/outputs
- View traces associated with each run
- View high-level metrics for each run
Trace Grouping
Traces can now be grouped based on the trace function, and the component function. Trace groups together at the root level, while component allows for sub-groups.- New function added:
trace - New function added:
component
CLI Improvements
Our CLI has been improved to provide a better developer experience.- AgentMark
initcan optionally create an example app - Added
pull-modelsto walk through adding new models to your platform
Bug Fixes
- Fixed a bug which could cause an app’s templates to be deleted when a new app was created
- Fixed a bug which could cause some branches not to show up in the UI
- Fixed a bug which could prevent newly created local prompts from being synced to the platform
Other
- Improved UI for prompts input/output
- Paginate traces
- Improved UI theme for prompts
Overview
AgentMark is a git-based Prompt Engineering Platform that empowers both application developers and prompt engineers to collaborate seamlessly on GenAI products. AgentMark enables application developers to manage their configuration, prompts, datasets, and evals in a git-based workflow while also providing a hosted platform for seamless collaboration with non-technical team members.Features
- Prompt Management
- Observability
- Datasets
- CLI
- Platform Management
- Evals
Prompt Management
AgentMark takes a developer-first approach to prompt management, treating prompts as files that live in your repository while still providing a platform for non-technical team members. All prompts are saved in AgentMark, a markdown-based format that is easy to write and read.Read DocsObservability
We build on top of OpenTelemetry for collecting telemetry data from your prompts. This helps you monitor, debug, and optimize your LLM applications in production. We provide traces, logs, metrics, and more.Read DocsDatasets
Create datasets to test easily test your prompts in bulk against a large set of data.Read DocsCLI
We provide a CLI for initializing your AgentMark app, customizing it, and deploying it to the cloud. Add new models to your platform with just a single command. You can also develop w/ AgentMark locally using our serve command.bash
Platform Management
AgentMark offers an intuitive platform for creating new git-synced apps, adding team members with roles, and setting up API keys for users.AgentMark SDK
AgentMark’s SDK is simple and easy to use. We offer features like: one-LOC observability, securely fetching prompts from our CDN, and more.Read Docs
Features- Initial release of AgentMark
- Support for OpenAI, Anthropic, and other LLM providers
- MDX-based prompt templating
- Type-safe prompt development
- Tools and agents support
- Added comprehensive documentation
- Included examples and guides
- API reference documentation