See which coding session needs you and return to its conversation, with terminal processes that keep running while you detach.
In the practical guideCan I leave a review running and come back to it?Read guideDocs checked
The AI tools guide
AI tools,
put to work.
Find tools for coding, agents, research, automation, writing, images, video and audio. Compare the job, access and limits, then use one of six practical guides or explore a sourced product profile.
Inside the Codex guide
CodexOpenAIWhy did one request create two tickets?
Explore unfamiliar code, work out how to check a change and make the edit with help from OpenAI’s terminal coding assistant.
Read the walkthrough
The directory
Choose a tool.
Manus suits a task whose answer needs to become a deliverable: a source-linked briefing, slides or a small website. Agent mode plans and performs multi-step work, while Chat mode offers a lighter conversation.
Illustrative workflowCompare three public toolsRead profileDocs checked
Perplexity is a starting point for a question that needs current web evidence and citations the reader can inspect. Search and deeper research can bring several sources into an answer; file analysis and model selection depend on the plan.
Illustrative workflowCompare competing release claimsRead profileDocs checked
Notion AI is useful when the question and its supporting material already live in a team's Notion workspace. It can find and transform that knowledge, search connected apps and the web, draft or edit documents, analyze files and populate database summaries.
Illustrative workflowSummarize a project decisionRead profileDocs checked
Cursor brings coding assistance into work on an existing repository through editor, CLI and cloud-agent surfaces. Agent can search files, edit code and run commands; Ask provides a read-only exploration option.
Illustrative workflowRepair a synthetic parsing bugRead profileDocs checked
Replit Agent is a build-and-deploy environment for someone who wants to make an app without first preparing a local development setup. Describe a small application, review the plan and iterate in the project editor before deliberately publishing.
Illustrative workflowBuild a synthetic equipment checkout appRead profileDocs checked
n8n combines explicit workflow logic with model-driven steps, so a repeatable process can reserve AI for the part that needs interpretation. It is available as managed Cloud and self-hosted software under fair-code terms that need checking for the intended use.
Illustrative workflowDraft a support-ticket routeRead profileDocs checked
Make AI Agent (New) places agent work inside a cloud automation scenario. Configure instructions, a provider, knowledge, inputs and tools, then test the agent as part of that scenario.
Illustrative workflowDraft an internal inquiry routeRead profileDocs checked
Zapier is moving its standalone Agents product into AI by Zapier steps in the Zap editor. As of October 2, 2026, no Agents shutdown date has been announced.
Illustrative workflowReview a migrated draft-generation workflowRead profileDocs checked
Lovable develops web apps from a natural-language description into editable code, backend behavior and a deployment workflow. It suits a small app whose owner wants to iterate in a preview before deciding what should be published.
Illustrative workflowPrototype an equipment reservation appRead profileDocs checked
Make the choice around your work
Which tool fits your workflow?
Start with a task above, or add up to three tools. These starting sets are examples, not rankings.
Three ways to read the landscape
Start with the work. Then trace the product.
These maps explain the directory’s organization. Category membership is editorial task fit, not a measured ranking or a complete product inventory.
01 / Jobs → tools
A tool can belong to several jobs. Follow a category to filter the same directory above.
- CodingUnderstand, change and review a codebase.7 tools
- AgentsDelegate a bounded task or coordinate assistant sessions.10 tools
- ResearchFind and compare sources for a question.4 tools
- AutomationConnect tools and turn repeated work into a workflow.4 tools
- WritingDraft and revise documents with explicit sources and an audience.5 tools
- ImagesGenerate or edit visual material from a brief.5 tools
- VideoGenerate, assemble or edit moving images.5 tools
- AudioCreate speech or music and edit recordings.4 tools
02 / Companies → product surfaces
The company builds or offers the named surfaces below. Applications, models and developer platforms occupy different layers; an account for one does not establish access to another.
OpenAI
Read the relationships and sourcesAnthropic
- model familyClaude models
- applicationClaude
- coding agentClaude Code
- work agent productClaude Cowork
- research organizationGoogle DeepMind
- model familyGemini models
- applicationGemini app
- developer platformGoogle AI Studio and Gemini API
Microsoft
- organizationMicrosoft AI
- application familyMicrosoft Copilot
- work applicationMicrosoft 365 Copilot
- coding assistantGitHub Copilot
Meta Platforms
- assistant application and integrationsMeta AI
- research organizationMeta Superintelligence Labs
- model seriesMuse model series / Muse Spark
- personal agent productMuse personal agent
xAI / SpaceXAI
- model familyGrok models
- applicationGrok assistant
- developer apiGrok API
- coding agentGrok Build
03 / Brief → artifact → review
An illustrative workflow for choosing and evaluating a tool, not an executed benchmark.
- Define the output
A code patch, cited answer, workflow, image, video or audio deliverable.
- Choose the surface
Compare the product profile’s account, platform, input rights and processing path.
- Try a bounded example
Use the proposed public or synthetic inputs. Read a practical guide when one is available.
- Verify the artifact
Inspect the citations, behavior, rights and error paths before relying on the result.
02Learning paths
Start with the job.
Make a code change, review a pull request, or coordinate a few agents. These walkthroughs show how to use the tools along the way.
Learning path · 5 steps
Handle HTTP errors and ambiguous writes in a small client
Start with the supplied support-service client and finish with a reviewed patch, regression tests and a short explanation of its behavior. The same two files carry the work from the first question to the final check: one mistakes an HTTP error for ticket data, while the other repeats a write after an ambiguous failure.
Leave withYou will produce two corrected modules, focused regression tests, and a change note a reviewer can use. No web server, real tickets or package installation is needed for the JavaScript project. Install and authorize one of the linked assistants separately.
Step 1 of 5
Get a known starting point
Unpack the starter into a disposable folder and install one assistant you are authorized to use. Read the README and run the happy-path tests. Run each contract check separately to see the supplied defects before asking for a fix. These failures are expected in the teaching project.
CheckpointBoth baseline tests pass. The 503 contract and ambiguous-write contract fail for reasons you can explain.
Read the Codex guidePlanned coverageComing soon10 tools · 4 paths
These deeper practical walkthroughs are planned. A sourced product profile may already be available above.
Run local models
How much model can your hardware comfortably run, and what work will it be good for? This planned guide will connect model choice and local processing with a task you can try. It is not ready yet.
Connect your data
A planned guide to giving an assistant a small approved source to search, then following its answers back to the original material. Setup and the worked example are still being reviewed.
Evaluate quality and cost
Which tool leaves you with more useful work after mistakes, retries and review time are counted? This planned guide will explain how to compare the same tasks fairly. It is not ready yet.
Monitor production AI
A planned guide to following an AI request through its model and tool calls, so you can understand a failure or an unexpected bill. The guide is still being prepared.
OpenAI API
For building an application that calls OpenAI models directly. The planned guide will cover access, authentication, usage controls and data handling. If you want help working in a repository, the Codex guide is available now.
Anthropic API
For applications that call Anthropic models directly. Access, authentication, usage controls and data handling will be covered in a separate guide. For work inside a codebase, start with Claude Code.
Ollama
Planned coverage will connect hardware requirements and model choice with a useful local task. The installation instructions and example still need a full documentation review.
LM Studio
The future guide will explain setup, model choice and where your data is processed. Its first worked example is still to be reviewed.
OpenRouter
A planned guide to understanding which provider handles a model request, what terms apply and how it is billed. The profile is not ready yet.
n8n
The planned guide will follow an automation from its input through the services and credentials it needs. Setup and the worked example still need review.
Langfuse
Planned coverage will explain how to inspect model requests and evaluate their results, including what information is sent to the service. The guide is still being prepared.
Phoenix
A planned guide to examining AI behavior and tracing where evaluation data goes. Setup and the worked example still need a full review.
Promptfoo
The planned guide will show how to compare results on the same task and understand what the tests establish. Current installation instructions and the example still need review.
LangGraph
A planned guide to how an agent workflow tracks its progress and resumes after an interruption. The setup and first worked example still need review.