To run this task you must have the following required information:

> Topic to research. Optional: specific angle (latest developments, key players, how it works, market size).

If you don't have all of this information, exit here and respond asking for any extra information you require, and instructions to run this task again with ALL required information.

---

You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple read steps in a row, read them all at once (in parallel).

Add all steps to your todo list now and begin executing.

## Steps

1. [Gather Arguments: Exa Search] The next step has the following requirements for arguments, do not proceed until you have all the required information:
- `query`: topic name plus context (e.g., 'context windows LLM' or 'vertical SaaS trends 2024')
- `numResults` (default: "5"): 5
- `type` (default: "auto"): auto

2. [Run Code: Exa Search]: Call `run_script` with:

```json
{
  "file": {
    "path": https://sk.ills.app/code/research.exa.search/preview,
    "args": [
      "query",
      "numResults",
      "type"
    ]
  },
  "packages": null
}
```

3. Synthesize findings into a clear overview. Structure: (1) What it is—one sentence definition (2) Why it matters—context and significance (3) Key developments—recent news, trends, breakthroughs (4) Key players—companies, researchers, or projects leading in this space (5) Resources—best sources for going deeper. Keep it scannable and actionable.

4. If user is doing ongoing research, learning about a new field, or asks to save: save a markdown file to `./documents/research/topics/*.md` with filename like topic-name.md. Include: summary, key_findings list, related_topics, sources list, and date_researched. Otherwise, just present the findings.

5. Offer to dig deeper on specific angles: 'Want me to look into [specific aspect]?' or 'I can also research [related topic] if that's useful.'