When to Use
User has a research question or knowledge gap. Agent takes ownership of the full research cycle: scanning literature, generating hypotheses, running analyses, synthesizing findings. Human provides direction and oversight, AI executes.
Quick Reference
| Topic |
File |
| Research pipeline |
pipeline.md |
| Risk mitigation |
risks.md |
Core Concept
Traditional research: Human-led, human-executed
Deep research: Human-led, AI-assisted
Vibe research: Human-directed, AI-led
The human sets the question and validates outputs. The agent handles literature synthesis, hypothesis generation, data analysis, and write-up autonomously.
Core Rules
1. Full-Cycle Ownership
Agent executes the complete pipeline:
- Gap identification — What's unknown or contested?
- Literature synthesis — Scan, summarize, cross-reference sources
- Hypothesis generation — Propose testable claims
- Analysis design — Define methodology
- Execution — Run analyses, gather data
- Synthesis — Write findings with citations
2. Vision from Human, Execution from Agent
- Human provides: research question, domain constraints, success criteria
- Agent handles: reading papers, connecting ideas, running experiments, drafting
- Human validates: key decisions, final outputs, methodology choices
3. Transparent Reasoning
- Cite every claim: source, page, quote
- Show reasoning chain for hypotheses
- Log all analytical steps for reproducibility
- Flag confidence levels (high/medium/low)
4. Proactive Gap Detection
Don't wait for instructions. When analyzing a topic:
- Identify contradictions in literature
- Spot under-explored areas
- Suggest follow-up experiments if results are ambiguous
- Pull additional sources when context is insufficient
5. Hallucination Prevention
- Only claim what sources support
- Distinguish: "Source X says..." vs "I infer..."
- When uncertain, say so explicitly
- Cross-verify critical facts across multiple sources
Vibe Research Traps
- Treating AI output as ground truth → always require human validation of key findings
- Skipping methodology transparency → document every step for reproducibility
- Overwhelming human with raw output → synthesize into actionable insights
- Losing the human's analytical skills → keep them engaged in critical thinking
1---2name: vibe-research3description: Conduct AI-led research with autonomous literature review, hypothesis generation, analysis, and synthesis while human provides vision.4---5
6## When to Use
7
8User has a research question or knowledge gap. Agent takes ownership of the full research cycle: scanning literature, generating hypotheses, running analyses, synthesizing findings. Human provides direction and oversight, AI executes.
9
10## Quick Reference
11
12| Topic | File |
13|-------|------|
14| Research pipeline | `pipeline.md` |
15| Risk mitigation | `risks.md` |
16
17## Core Concept
18
19**Traditional research:** Human-led, human-executed
20**Deep research:** Human-led, AI-assisted
21**Vibe research:** Human-directed, AI-led
22
23The human sets the question and validates outputs. The agent handles literature synthesis, hypothesis generation, data analysis, and write-up autonomously.
24
25## Core Rules
26
27### 1. Full-Cycle Ownership
28Agent executes the complete pipeline:
291. **Gap identification** — What's unknown or contested?
302. **Literature synthesis** — Scan, summarize, cross-reference sources
313. **Hypothesis generation** — Propose testable claims
324. **Analysis design** — Define methodology
335. **Execution** — Run analyses, gather data
346. **Synthesis** — Write findings with citations
35
36### 2. Vision from Human, Execution from Agent
37- Human provides: research question, domain constraints, success criteria
38- Agent handles: reading papers, connecting ideas, running experiments, drafting
39- Human validates: key decisions, final outputs, methodology choices
40
41### 3. Transparent Reasoning
42- Cite every claim: source, page, quote
43- Show reasoning chain for hypotheses
44- Log all analytical steps for reproducibility
45- Flag confidence levels (high/medium/low)
46
47### 4. Proactive Gap Detection
48Don't wait for instructions. When analyzing a topic:
49- Identify contradictions in literature
50- Spot under-explored areas
51- Suggest follow-up experiments if results are ambiguous
52- Pull additional sources when context is insufficient
53
54### 5. Hallucination Prevention
55- Only claim what sources support
56- Distinguish: "Source X says..." vs "I infer..."
57- When uncertain, say so explicitly
58- Cross-verify critical facts across multiple sources
59
60## Vibe Research Traps
61
62- Treating AI output as ground truth → always require human validation of key findings
63- Skipping methodology transparency → document every step for reproducibility
64- Overwhelming human with raw output → synthesize into actionable insights
65- Losing the human's analytical skills → keep them engaged in critical thinking
modbender