Ask for source-backed facts, distinguish facts from hypotheses, and require an explicit “not found” when evidence is unavailable. Human review remains required before research affects scoring, CRM data, or messaging.
Before you start
- Define the decision the research must support.
- Choose the company, person, signal, region, and time period in scope.
- List the public or approved sources that may be used.
- Decide the output language and maximum useful length.
- Identify sensitive information that must not be collected or used.
Build the prompt from six components
| Component | Specify |
|---|
| Decision | Qualify, prioritise, verify, or select a conversation angle. |
| Scope | Company, person, event, geography, and time window. |
| Questions | A short list of verifiable questions. |
| Evidence | A source or public proof for every factual claim. |
| Output | Language, headings, concise format, and not-found behaviour. |
| Safety | No private, sensitive, credential, or unsupported personal information. |
Separate facts from interpretation
Ask the result to label direct evidence, derived interpretation, and unresolved questions separately. A plausible sentence without a source is still unverified.
- Fact: a source directly supports the statement.
- Hypothesis: an interpretation that must be labelled and reviewed.
- Not found: available sources do not support an answer.
- Outdated: evidence may no longer reflect the current company or role.
- Sensitive: information that must not be used for outreach.
Steps
- **Define the decision. **Write what will change if the research confirms or rejects the hypothesis.
- **Add scope and exclusions. **Name the signal, time window, geography, company or person, and what should be ignored.
- **Ask focused questions. **Use a small set of questions that can be answered with evidence.
- **Require sources. **Request proof for every factual claim and “not found” when none exists.
- **Specify the output. **Choose language, headings, length, and separate facts, hypotheses, and gaps.
- **Test known accounts. **Run the prompt on at least five positive, negative, and edge cases.
- **Review before use. **Check sources, identity, dates, and relevance before copying results into scoring, a message, or the CRM.
How a research run works
Signalist researches the lead's company and the lead at the same time, collects the facts it finds together with their sources, and then writes the result in the structure your prompt asks for. A run usually takes a few minutes.
- Company research is reused. When you research another lead at the same company with the same prompt within 14 days, Signalist reuses the company research and only researches the person, so that result is ready sooner. Signalist recognises the company by its website. Company facts in a result can therefore be up to 14 days old; research about the person is always new.
- The result is written from the facts found. If a run finds no usable facts, it ends as not completed: nothing is saved and no credits are charged.
- A completed research is charged once, when its result is saved.
Follow a research run
When you start Deep Research for a lead, its status shows on the lead's Research tab, in the Research column of a list (switch it on under Columns), and on the lead cards in the campaign builder:
- Queued, for example "Queued · 5 min": the research is waiting for a free slot and starts as soon as one opens.
- Researching…, for example "Researching… · 3 min": the research is running.
- After 20 minutes Signalist adds "Taking longer than usual". The research is still going, so there is no need to start it again.
- If the research could not be completed, the Research tab says "The last research could not be completed." Click Try again to start it again. An earlier result for the lead stays visible below.
- If your balance cannot pay for the research, the tab says "Not enough credits for Deep Research". Add credits under Company Settings → Plans & Billing and start it again.
The status stays when you reload the page or open the lead later.
Review and safety checks
- Every question supports a real decision.
- The scope and time window are clear.
- Factual claims include usable evidence.
- Hypotheses and gaps are labelled.
- Sensitive or private information is absent.
- The output is concise enough for review.
- No statement enters outreach or scoring without human validation.
Troubleshooting
| Problem | Solution |
|---|
| The result is long but not useful | Reduce the questions and connect each to qualify, prioritise, verify, or select an action. |
| The answer contains unsupported claims | Require sources and “not found”; remove unsupported text from downstream use. |
| Sources are old | Add a time window and require a publication or observation date. |
| The wrong person or company was researched | Add stable identifiers and current company context, then discard the mismatched result. |
| Different languages appear | Specify one output language and test records from multiple regions. |
| The research stays on Queued for a while | Many runs are waiting for a slot. The research starts by itself; you do not need to start it again. |
| A company fact changed in the last two weeks | Company research is reused for 14 days. Check the source date before using the fact. |
Frequently asked questions
What should a Deep Research prompt start with?
Start with the decision, then define scope, questions, evidence, output, and safety rules.
How many questions should I ask?
Use the smallest set that changes the decision. Fewer focused questions are easier to verify.
Can results be used directly in a message?
No. Check the source, date, identity, relevance, and wording first.
What happens when no source is found?
The output should say “not found” or identify the gap, not generate a plausible substitute.
Why was the second lead at a company researched faster?
Signalist reused the company research from the first lead (same company, same prompt, within 14 days) and only researched the person.
Can I ask for private personal information?
No. Use only necessary, approved, and appropriate sources and exclude sensitive information from outreach.
Where can the prompt be reused?
Use the Deep Research prompt or Templates workflow available in your workspace, then test each downstream use.
Keep reading
Set up copywriting, prompts, and templates
Signalist's AI writes your messages from what it knows about the lead, your company, and your rules. You shape the result in four places: the Copywriting page, your personal copywriting settings, the Templates page, and AI snippets inside a message.
Review and approve the Knowledge DB
The Knowledge Base tells the AI what you sell, to whom, and why it matters. Signalist builds a first version for you from your answers and your website. Review it, correct what is wrong, and approve it, because your AI messages and research draw on it.
Understand P1, P2, P3, and DQ
Every scored lead gets one grade: P1 , P2 , P3 , DQ , or ? . The grade says how well the lead fits the companies and people you defined under Lead Scoring . It is calculated from points, so you can always trace why a lead got its grade.
