Agent reference
Technical specifications for Boki's AI agents
Agent reference
Technical specifications for all Boki agents.
Global chat agent
The primary interface accessed via the orange sparkle icon.
Modes
| Mode | Behavior |
|---|---|
| Auto | Boki decides approach based on query — may search web, analyze workspace, or combine |
| Research | Prioritizes web search and external source analysis |
Context
- Has access to workspace content (plans, briefs, articles)
- @ mentions load specific document content into context
- Conversation history persists within session
Greeting
Initial message: "Hi! I'm Boki."
Researcher agent
Specialized agent for deep research tasks.
Capabilities
| Capability | Description |
|---|---|
| Web search | Searches public web for relevant content |
| Source analysis | Evaluates and summarizes sources |
| Competitive analysis | Compares your content against external content |
| Gap identification | Finds topics and angles not covered by competitors |
Artifacts (Beta)
| Artifact | Description |
|---|---|
| Outlines | Suggested content structure |
| Keyword clusters | Related terms grouped by intent |
| Source lists | Curated sources with summaries |
Limitations
- Cannot access paywalled content
- Web search results may not include very recent content
- Does not write full articles
Technical review agent
Reviews content for technical accuracy.
Requirements
- Minimum 50 words of selected text
- Works in article editor only (inline)
Capabilities
| Check | Description |
|---|---|
| Code verification | Syntax checking, logic review |
| Sandbox execution | Can run code to verify behavior |
| Fact-checking | Verifies technical claims against sources |
| Consistency check | Ensures terminology and examples are consistent |
Output
Returns structured feedback with:
- ✓ Verified elements
- ⚠ Issues requiring attention
- 💡 Suggestions for improvement
Marketer review agent
Reviews content for marketing effectiveness.
Requirements
- Minimum 50 words of selected text
- Works in article editor only (inline)
Evaluation criteria
| Criterion | Description |
|---|---|
| Structure | Logical flow, transitions, opening/closing |
| Funnel alignment | Matches intended stage (awareness/consideration/decision) |
| Source quality | Claims supported by credible sources |
| Clarity | Main point clear, jargon explained |
Output
Returns structured feedback with:
- Identified issues
- Specific improvement suggestions
- No grammar or spelling checks (not the purpose)
LLM search visibility agent
BetaScores content against specific questions for AI visibility.
Requirements
- Minimum 50 words of selected text
- A specific question to score against
- Works in article editor only (inline)
Scoring factors
| Factor | Weight | Description |
|---|---|---|
| Question alignment | High | Does content directly answer the question? |
| Comprehensiveness | High | Thorough coverage of topic |
| Authority signals | Medium | Clear definitions, structure, citations |
| Differentiation | Medium | Unique value not in competing content |
Score interpretation
| Range | Meaning |
|---|---|
| 80-100 | Strong — likely cited as primary source |
| 60-79 | Moderate — may be cited, competing content stronger |
| 40-59 | Weak — unlikely cited without improvements |
| 0-39 | Poor — doesn't address question adequately |
Output
Returns:
- Numeric score (0-100)
- Strengths of the content
- Gaps compared to competing content
- Specific suggestions
Limitations
- Score is predictive, not definitive
- Different LLMs may weight factors differently
- Does not measure traditional SEO ranking
Common limitations (all agents)
- Agents do not write full articles
- Agents provide advisory feedback — user decides what to act on
- Agents cannot access your account credentials or external services
- Agent capabilities may vary based on plan tier