Egret AI System — Search Quality Input

Egret AI System — Recruiter Input Guide: what this is, why your input matters, and how to fill out the form so the AI learns from our best work — not generic recruiting logic. Tips and examples appear under the most important questions below.

Section 1: About The Search

Write it the way you'd say it out loud to a colleague, not the way it reads in the job description.

Question 0 — How would you describe this search in your own words?

Why this matters

This is the single most important field for the AI system. It becomes the actual search query the AI runs against our candidate database — so it needs to sound like how you would say it out loud to a colleague, not how it reads in the job description. Include the role, the channel side, geography, and one or two non-negotiable signals.

Examples

Too vague

“Looking for a sales manager with electrical industry experience in the South.”

Specific and useful

“Regional Sales Manager for an electrical distributor in TX, LA, and MS — needs distributor-side experience, branch P&L ownership, and a track record coaching sales teams.”

Section 2: Candidate 1

For each candidate who was presented or placed, answer every question as specifically as you can.

Use the candidate’s full name — we match names to database records on the back end. Crelate IDs help if you have them but are not required. More in FAQ

Question 1 — Why were they a strong fit?

Why this matters

This is the core of the whole exercise. The AI needs to understand your reasoning, not just the outcome. Two or three specific sentences beats a paragraph of generalities. Name the actual signals — the companies they worked for, the territory they knew, the relationships they had, the specific experience that mattered.

Examples

Too vague

Strong background in lighting sales with good distributor relationships and solid communication skills.

Specific and useful

Donna spent 8 years at Acuity Brands as a territory rep in the Southeast and knew every major lighting distributor in the region personally. She had already called on three of this client’s top target accounts. Her existing relationships would have cut 6-12 months off the client’s market penetration timeline.

Question 2 — The junior recruiter briefing

Why this matters

This is the most powerful question on the form. It forces you to articulate the pattern — the combination of background, channel experience, geography, and intangibles that made this candidate right. That pattern is exactly what we need the AI to recognize in future searches.

Examples

Too vague

Look for someone with lighting experience and good communication skills who knows the territory.

Specific and useful

Look for manufacturer-side lighting experience specifically — not distributor side. They need to know the commercial construction channel and have existing distributor relationships in the territory. Rep agency background is a bonus. Don’t bother with anyone who has only worked industrial or utility — completely different sale and the client will know immediately.

Section 3: Candidate 2

Complete every field for this candidate.

Question 1 — Why were they a strong fit?

Why this matters

This is the core of the whole exercise. The AI needs to understand your reasoning, not just the outcome. Two or three specific sentences beats a paragraph of generalities. Name the actual signals — the companies they worked for, the territory they knew, the relationships they had, the specific experience that mattered.

Examples

Too vague

Strong background in lighting sales with good distributor relationships and solid communication skills.

Specific and useful

Donna spent 8 years at Acuity Brands as a territory rep in the Southeast and knew every major lighting distributor in the region personally. She had already called on three of this client’s top target accounts. Her existing relationships would have cut 6-12 months off the client’s market penetration timeline.

Question 2 — The junior recruiter briefing

Why this matters

This is the most powerful question on the form. It forces you to articulate the pattern — the combination of background, channel experience, geography, and intangibles that made this candidate right. That pattern is exactly what we need the AI to recognize in future searches.

Examples

Too vague

Look for someone with lighting experience and good communication skills who knows the territory.

Specific and useful

Look for manufacturer-side lighting experience specifically — not distributor side. They need to know the commercial construction channel and have existing distributor relationships in the territory. Rep agency background is a bonus. Don’t bother with anyone who has only worked industrial or utility — completely different sale and the client will know immediately.

Section 4: Candidate 3

Complete every field for this candidate.

Question 1 — Why were they a strong fit?

Why this matters

This is the core of the whole exercise. The AI needs to understand your reasoning, not just the outcome. Two or three specific sentences beats a paragraph of generalities. Name the actual signals — the companies they worked for, the territory they knew, the relationships they had, the specific experience that mattered.

Examples

Too vague

Strong background in lighting sales with good distributor relationships and solid communication skills.

Specific and useful

Donna spent 8 years at Acuity Brands as a territory rep in the Southeast and knew every major lighting distributor in the region personally. She had already called on three of this client’s top target accounts. Her existing relationships would have cut 6-12 months off the client’s market penetration timeline.

Question 2 — The junior recruiter briefing

Why this matters

This is the most powerful question on the form. It forces you to articulate the pattern — the combination of background, channel experience, geography, and intangibles that made this candidate right. That pattern is exactly what we need the AI to recognize in future searches.

Examples

Too vague

Look for someone with lighting experience and good communication skills who knows the territory.

Specific and useful

Look for manufacturer-side lighting experience specifically — not distributor side. They need to know the commercial construction channel and have existing distributor relationships in the territory. Rep agency background is a bonus. Don’t bother with anyone who has only worked industrial or utility — completely different sale and the client will know immediately.

Section 5: What Made This Search Work

These questions capture the recruiting instincts that never appear in a job description. Be as specific and candid as possible.

Question 3A — What signals in the candidate background showed a fit?

Why this matters

Spell out the concrete signals in the candidate’s background that made them right — companies, channel side, territory, relationships, and specific experience. The AI learns from named signals, not from phrases like “strong background” without detail.

Example

8 years on the manufacturer side in Southeast lighting, existing relationships with top regional distributors, and prior ownership of a branch-level P&L.

Question 3B — What did the client really care about?

Why this matters

Job descriptions never tell the whole story. The hidden criteria — existing relationships, cultural fit, growth potential, specific competitor experience — are often what actually decided the placement. If you know what the hiring manager really cared about, document it here.

Example

Specific and useful

The hiring manager cared more about existing distributor relationships than anything on the job description. They had a bad experience with a technically strong candidate who couldn’t build internal relationships, so they were specifically watching for EQ and coachability. The comp range was also flexible for the right person — they never put that in writing.

Question 4 — Who looked good on paper but was wrong?

Why this matters

False positives are as important as true positives for training. If a candidate had an impressive resume but fell flat for a reason that wasn’t obvious from their profile, that’s critical signal. The AI needs to learn what to avoid surfacing, not just what to surface.

Example

Specific and useful

We presented one candidate from a top manufacturer with a perfect resume who fell flat in the first interview. He had been in a large corporate role with full support staff and couldn’t articulate how he would build a territory from scratch. The client picked up on it immediately. On paper he was stronger than the candidate we placed.

What we’re building and why your knowledge is the key ingredient

We’re building an AI assistant that searches our 121,000-contact database and surfaces the best candidates for any new search. Think of it as a very fast junior researcher who never forgets a contact — but only as good as what it has been taught about what good looks like at Egret.

The problem: no off-the-shelf AI understands the difference between a manufacturer-side candidate and a distributor-side candidate. It doesn’t know why an LC credential matters for a lighting controls role, or why someone from a large corporate manufacturer might be wrong for a scrappy startup client. Only we know that — and we need to teach it.

Your past placements and strong presentations are the training data. The form captures your recruiting instincts in a structured way so the AI can learn from them. There is no shortcut here — this is the most valuable thing you can do for the system.

  • 5–10 searches to document per recruiter
  • 2–4 candidates documented per search
  • ~30 min estimated time per search entry
  • 1 day total investment from the whole team

Back to form

Which searches to document

Pick searches where you remember the candidates clearly. These work best:

Placements that stuck past 6 months

These are your highest-quality examples. You know the candidate was right, the client was happy, and the placement held. Document everything you remember about why it worked.

Strong presentations that went to interview

Even if the search didn’t close, candidates who made it to interview represent real quality judgment. What made you confident enough to present them?

Candidates who looked good on paper but were wrong

These are just as valuable as the placements. The AI needs to learn what not to surface, not just what to surface. If you remember a candidate who had the right resume but failed for a non-obvious reason, document that too.

Aim for variety across market segments — don’t only document lighting searches if you also work distribution or automation. Each recruiter’s specialty is irreplaceable input for the segments you cover.

Back to form

How to fill out the form — step by step

  1. Pick your searches before you open the form. Spend 5 minutes writing down 5-10 searches you remember clearly before you start. Placements are ideal, strong presentations work too. Having them in mind first makes the form much faster to fill out. The very first question asks how you would describe the search in one or two sentences — having your answer ready before you open the form saves time and produces a better answer.
  2. Pull up Crelate for each search as you go. Having the candidate record open while you fill out the form helps. You don’t need to copy fields verbatim — you’re telling the story of why they were right, not transcribing their resume.
  3. Answer the why questions in plain language. Write the way you’d explain it to a colleague, not the way you’d write it in a presentation. Specific and conversational beats formal and vague every time. If you find yourself writing “strong background” or “excellent communicator” without backing it up with specifics, add the detail.
  4. Submit once per search, then submit another for the next one. The form is designed for one search per submission. When you finish a search entry, it will ask if you have another. This keeps responses clean and easier to process.
  5. Aim for 5-10 submissions; prioritize quality over speed. Five complete, specific entries are worth more than ten rushed ones. If you only have time for three really good ones this week, submit three and come back to the rest.

Back to form

How many searches and candidates do you need?

Across the whole team, we need 20-30 search entries with 2-4 candidates each. That gives the AI enough examples to learn meaningful patterns. Here is what we are aiming for:

Category Minimum Ideal
Total searches documented 20 30
Placed candidates 15 20
Presented but not placed 5 8
Strong but wrong candidates 3 5
Market segments covered 4 6
Functions covered (sales, eng, ops…) 3 5
Geographies covered 4 6

Back to form

Common questions

What if I don’t remember all the details?
Write what you remember. Partial information is still useful. The “why were they a strong fit” answer from memory is often richer than pulling it from notes because you are capturing what actually mattered, not what got written down at the time.
Do I need to look up Crelate IDs for each candidate?
No — just use the candidate’s full name. We will match names to database records on the back end. Crelate IDs are helpful if you have them but not required.
What if a search had only one strong candidate?
That’s fine — document that one candidate fully in the Candidate 1 section and leave Candidates 2 and 3 blank. One complete entry is better than three thin ones.
Should I document searches that didn’t result in a placement?
Yes, if you got to the presentation or interview stage. Candidates who were presented but not placed — and the reasons why — are valuable training data. Document what you know.
How long will this take?
About 20-30 minutes per search once you are in the rhythm. The first entry will take longer as you get familiar with the form. Budget 2-3 hours total for 5-8 searches, which can be done across a few sessions.
What happens with the information I submit?
Responses go into a secure internal system used only to train the Egret AI. Nothing is shared externally. Candidate and client information is used solely for improving our internal search quality.

Back to form

Thank you for taking the time to do this right.

Every answer you put into this form directly shapes what the AI learns about what good looks like at Egret. The more specific and honest your answers, the better the system will perform — and the more time it will save you finding the right candidates in future searches.

Back to form