Skip to content
AI Workflows

AI in the
background

Classification, extraction, scoring, drafting. Embedded inside your existing process, not in a chat window.

Hours of repetitive review, done in seconds. With audit trails.

The difference

Not every AI task needs a conversation.

Most of the time the right shape is an AI step plugged into a workflow you already run. The team never sees it. They just see the output.

Airtable Google Sheets Excel Gmail Slack HubSpot

Your Process

Claude OpenAI

AI Step

Human Checkpoint (optional)

Clean Output

Runs inside your existing tools Audit log on every classification Editable prompts your team can tune

Example

Inbound lead qualification

The same shape works for support triage, invoice review, or any other classify-then-act process.

Manual review

30 min per batch

Open each new contact form. Read what they want and who they are.

Check your ICP: industry, company size, geography. Does this lead actually fit?

Look the company up. New contact? Past lead? Already a customer?

Score the fit. Write a short note. Assign to a rep.

Repeat for every lead. Every week. Forever.

AI workflow

8 seconds
TechCorp · Series B SaaS, 200 staff qualified

Strong ICP fit. Route to senior rep.

Mid-market logistics, personal Gmail needs enrichment

Right industry. Verify the company before reaching out.

Solo freelancer, $200 budget not a fit

Outside ICP. Auto-reply with self-serve link.

Anonymous form, one-line request unclear

Not enough info to score. Send a clarifying email.

Every lead scored. Audit log per decision. Reps follow up on the qualified ones.

Case study Ingenieurbüro Hölzl GmbH

Proposal Eligibility Analysis for German Energy Subsidies

Hölzl is an engineering firm that helps homeowners claim German government subsidies for energy-efficient renovations. For every project, contractors send in a PDF proposal listing dozens of line items, and a consultant has to decide which ones the subsidy actually covers, line by line, against a thick rule book (the BEG EM).

We built a 6-stage pipeline that reads the PDF, looks up the relevant rules, and classifies every line with a written reasoning. What used to take 2-3 hours per proposal now runs in 12 seconds, and the consultant only reviews the flagged ones.

6 stage pipeline · per proposal

↓ see each stage in the live example below

1. Read the PDF

OCR the contractor's proposal into text

2. Pull out the line items

One row per item: position, description, qty, €

3. Look up the rules

Find the relevant passages in the rule book + FAQ

4. Load project context

Which measures is this project approved for?

5. Classify each line

Eligible / needs proof / unclear / not eligible, with written reasoning

6. Consultant review

Human approves the flagged lines only

Proposal Analyser

Project BEG EM 2000

Input

Stage 1
PDF

Proposal_47.pdf

Schreiner & Söhne GmbH

Project P-2026-0143
Total € 47,820
Line items 47
Processing 12.4s

Active measures

Stage 4

2.1 · Wall insulation

External wall (EWIS)

2.4 · Plinth insulation

5.1 · Energy consulting

Output summary

Stage 5
eligible 31
needs proof 8
unclear 5
not eligible 3

Classified line items

Stages 2 · 3 · 5
€26,460 eligible of €47,820
01 Mineral wool EWIS 160mm, 280m² €18,420 eligible
02 Aluminium base track 65mm €840 eligible
03 Scaffolding 280m², 6 weeks €4,260 needs proof

Confirmation it was used for insulation work.

04 Window sill extensions, 8 pcs €680 eligible
05 Plinth waterproofing (KMB) €1,140 unclear

Is the waterproofing within the insulated area?

06 Facade paint, colour finish €2,180 not eligible
07 Energy consulting + supervision €3,400 eligible
08 Disposal of old material, 4.2 t €520 eligible
09 Window replacement, U=0.95, 6 units €5,200 eligible
10 Roof insulation 180mm, 120m² €8,640 eligible
11 Internal wall painting, 220m² €1,920 not eligible
12 External door, U=1.1, 1 unit €2,340 eligible
+ 35 more lines · all classified
Stage 6 Consultant approved 31 lines · 8 flagged for proof

Results

Hours of rule-book reading, done in seconds.

12 sec

per proposal, down from 2-3 hours

1,500+

line items classified in production

96%

classification accuracy on the eval set

100%

decisions with written reasoning + audit trail

Our approach

How we build it with you.

Most AI workflows succeed or fail on two things: how carefully the AI step is set up, and where your team stays in the loop. We build with you until it's reliable enough to put your name on.

01

Find the work worth automating

We start by mapping where your team makes the same kind of decision over and over: classifying a message, scoring a lead, reviewing a line item, drafting the same response. That's where AI workflows pay back. We agree on the process before any AI gets involved.

We agree on: the steps, the rules, the volume

Where does manual judgment live?

Classifying contractor lines ~3h / proposal
Reading customer message history ~15min / customer
Scoring blog drafts for brand fit ~20min / draft
→ Picked for AI workflow highest leverage
analysis-step.contract.ts

// Input

line_id: UUID
description: string
qty: number
unit: string
active_measures: string[]

// Output

ai_status: 'eligible' | 'eligible_needs_proof'
         | 'unclear' | 'not_eligible'
ai_bucket: 'direct' | 'indirect' | 'planning'
         | 'unrelated' | 'unknown'
ai_reasoning: string
ai_proof_note: string | null

02

Agree on what goes in and what comes out

Before the AI does anything, we agree on exactly what it gets to see and exactly what it has to return. A fixed list of fields, a fixed list of allowed answers, written reasoning every time. That's the difference between AI that makes things up and a workflow your team can trust.

03

Decide where the human stays in the loop

Anything client-facing or high-stakes gets a review step. We agree the dials with you: auto-approve when the AI is confident, send to a human in the grey zone, reject below a floor. These are your numbers, not ones we bake in. Your team can adjust them at any time.

Confidence thresholds Approval queues Overrides feed back to the AI Full audit log

Decision routing

Auto-approve

confidence ≥ 0.85

78%

Send to human review

0.60 ≤ confidence < 0.85

18%

Reject + flag

confidence < 0.60

4%

Accuracy after each tuning round

Round 1 · first version 71%
Team overrode 12 decisions · added to the test set
Round 2 · prompt tweaked 88%
Team overrode 4 more · added an "unclear" option
Round 3 · live 96%

All tweaks done in a config table. No code changes.

04

Tune it with your team until it ships

Every change to the AI is saved as a version. Every time your team overrides a decision, that case gets added to the test set. Accuracy climbs from rough first draft to something you'd trust to run unattended in a few rounds, not a few weeks.

The instructions live in a config table you can edit. No code, no devs in the loop for small tweaks.

Capabilities

Four shapes the AI step takes.

Each one fits a different kind of repetitive work. Mix them inside one pipeline when the job calls for it.

Classify and tag

AI reads each incoming item and gives it a label, a status, or a score. The right ones go to the right place, your team only opens the ones that need them.

"Pool is green, 3rd time"

urgent

"How do I export?"

general

"Got the invoice, thanks"

no reply

Works for: support tickets, sales leads, line items, photo uploads, invoices.

Extract structured data

AI pulls the fields you care about out of PDFs, scans, or messy text and drops them into a clean table your other tools can use.

vendor Acme Co. invoice INV-2847 total $4,260.00 due 30 Jan 2026 items 12 lines

Works for: invoices, contracts, forms, transcripts, screenshots.

Draft with a quality gate

AI writes the first draft, then scores its own work against your standards. Anything below the bar is held back for a human, the rest goes straight out.

draft

brand
88
tone
92

Works for: listing descriptions, email replies, proposal copy, social posts.

Chain steps together

Several AI steps run on the same item, each one a specialist. Their results combine into a single decision: ship, send to review, or reject.

input

Fact 82
Brand 95
SEO 71

review

Works for: editorial pipelines, compliance checks, claims review, content moderation.

Every workflow we build includes

Human review on flagged items

Approval queues in Airtable, Slack, or your tool.

Editable instructions, no code

Your team tunes wording in a config table.

Full audit log on every decision

Who, when, what input, what reasoning.

Tunable thresholds

Adjust auto-approve and review bars any time.

More pipelines we have shipped

Three workflows. Same pattern.

Different domains, different inputs, different outputs, but the same shape underneath. Pick a pipeline to see how the AI step fits in.

Pick a pipeline

Customer Message Analyser

One AI step, three categorizations on every incoming message. Pick the example to see each in action.

1

Sentiment scoring

Reads the last few messages from one customer and scores how they're feeling.

Dec 18 · 09:14

"Pool is green again. Third time this month. What is going on?"

Sentiment score

42 /100

↓ declining trend

Tone worsened across 3 messages over 8 days. No callback logged. At-risk account, escalate to manager.

2

Needs response

Decides whether the message actually needs a human reply or just a logged acknowledgement.

Dec 12 · 14:22

"Thanks, got the invoice. Looks good. See you next week."

Needs reply

No

auto_acknowledge log_only

Confirmation message, no question asked. Bot sends a thanks-back. Saves the rep a context-switch.

3

Urgency detection

Flags safety risks and active incidents so they jump the queue, even out of hours.

Dec 19 · 22:47

"URGENT, pump leaking everywhere, pool draining fast!"

Urgency

Critical · page on-call

safety_risk active_incident after_hours

Equipment failure with damage risk. SMS sent to the on-call rep, ticket created at priority 1.

Input · scanned PDF

A 4-page contractor quote, scanned (not exported). Skewed, noisy, mixed fonts. The vision model still has to pull every row out cleanly.

PDF

Quote_0143.pdf

scanned, 4 pages

Source Contractor #042
Quality noisy scan, skewed
Vision Extractor

Output · structured table

Every line item parsed into a schema-validated row, then cross-checked against the project spec to flag anything off.

47

rows extracted

€47,820

total parsed

1

discrepancy

Pos Item
1.1 Insulation, 160mm 18,420
2.1 Scaffolding, 280m² 4,260
3.4 Waterproofing, 35 lm 1,140
+44 rows

Pos. 3.4 flagged · quoted 35 lm, project spec calls for 42 lm. Sent to the consultant for clarification before the proposal moves on.

DRAFT

Input · blog draft

"5 Trends Shaping the Category in 2026…"

6 agents · parallel scoring

each scores 0–100

Every draft is scored on six independent axes before anyone sees it. Each agent is a specialist with its own prompt and rubric.

Fact

82

3 claims verified

Social

76

hook strong

Virality

68

below target

Brand

95

on voice

SEO

71

3 keywords hit

Audience

78

resonates

Routing

aggregate 78 /100

Auto-approve

all ≥ 75

Human review

Virality 68 · 60–74

Reject

any < 60

Field service · Customer sentiment Customer message history scored daily, at-risk accounts flagged for the team

Same shape, every time

Input contract → AI step → structured output → checkpoint. The pattern repeats across domains.

Production-grade

Retry logic, fallbacks, rate limiting, eval sets. Every pipeline is built to run unattended.

Tunable by your team

Thresholds, prompts, rubric weights, all editable in a config table. No code change to retune.

Is this right for you?

Three signs an AI workflow will pay off.

A quick gut-check. If two of these three describe you, the workflow will earn its keep.

01

Someone is making the same call over and over

Classifying a message. Scoring a lead. Reviewing a line item. Drafting the same kind of reply. Same shape of decision, same rough rules every time.

20+ times a week

At this volume the workflow pays back in weeks, not quarters.

02

The data already lives in tools we can read

If your inputs are already in your CRM, your inbox, Airtable, or cloud storage, we plug the AI step into what you already use. No new platform for your team to learn.

We plug into

Airtable
Gmail
Slack
HubSpot
Google Sheets
+ anything with an API

If the data only lives in someone's head, we'd need to collect it first. That's a different project.

03

A human can catch the rare edge cases

The AI doesn't need to be perfect. It needs to be confident when it's right, and flag when it's not. Anything high-stakes goes through a review step before it ships.

80/20

AI handles the 80% your team would decide the same way every time. Humans focus on the 20% that actually needs judgment.

If two of those three sound like you, we should talk.

30-minute scope call. We pick the highest-leverage spot and quote a fixed price.

Book a scope call

Need autonomy and conversation instead of background processing? See AI Agents.

Ready to buildyour workflow?

30-minute scope call. We look at where the repetitive judgment lives, pick the highest-leverage spot, and quote a fixed price.

Book a Scope Call

No commitment required

30

min call

Fixed

price quote

2-3

week MVP guarantee