Owner Decision Memory
Turn the decisions you make repeatedly into rules the business can use.
How a call you have made fifty times becomes a written rule Deptly can apply — with you approving every rule, and every edge case coming back to you.
What does this layer do?
Owner decision memory turns the calls you make over and over — discount limits, who handles which kind of job, when a fee gets waived — into written rules Deptly can apply on your behalf. You approve every rule before it takes effect, you can read, edit, or retire any of them, and situations that do not cleanly match a rule come back to you as questions, not guesses.
The decisions you keep making
Some interruptions are genuinely new decisions. Most are not. Can we give a repeat customer a discount, does the deposit apply to this kind of job, which tech should take the nervous first-time customer, do we squeeze in the Friday request — you have answered each of these dozens of times, and the answer is almost always the same.
The cost is not any single interruption; it is that the business cannot move without you, because the decision logic lives only in your head. That is the owner-dependent pattern: not a competence problem, just knowledge that has never had anywhere else to live.
From one-off answers to standing rules
Decision memory gives that logic somewhere to live. It starts during onboarding, where you set the rules you already know — approval thresholds, deposit policy, escalation paths. Then it grows from the approvals themselves: when Deptly notices you have answered the same question the same way several times, it proposes a rule in plain language.
A proposal might read: repeat customers may be offered up to 8 percent off installs without asking; first-time customers stay at 5. You approve it, edit it, or decline it. Only approved rules take effect, and every rule stays readable — you can open the list any time and see exactly what Deptly is allowed to decide on your behalf.
From then on, that class of question stops reaching you, and the weekly brief shows you where the rule was applied. The decision still gets made your way — it just no longer needs you present to make it.
What kinds of rules it holds
Approval thresholds: the dollar amounts, discount percentages, and refund limits under which Deptly may act, and above which it must ask. Pricing exceptions: which customers or situations get different treatment, scoped so an exception never quietly becomes the default.
Escalation rules: what goes to you immediately, what can wait for the brief, and who gets asked when you are unreachable. Staff fit: which provider or crew suits which customer, job type, or situation — the matching logic you currently run in your head every morning.
Tone and special handling: how your business speaks, which customers need extra care, which topics you always want to handle personally. Rules are as much about how things are done as whether they are done.
The rules stay yours
Deptly never promotes a pattern to a rule on its own — every rule begins as a proposal you explicitly approve, and rules never extend their own scope. A discount rule for repeat customers does not creep to new customers because the situations look similar.
Near-misses escalate. When a situation almost matches a rule but not quite — the amount is slightly over, the customer is borderline repeat — Deptly asks rather than stretching the rule. Your answer can then refine the rule, if you want it to.
And some decisions can never become rules at all. Legal positions, clinical judgments, safety calls, insurance coverage determinations, and fiduciary choices stay with you or a qualified professional every single time — no threshold setting changes that.
What it works from
- Rules you set explicitly during onboarding: thresholds, exceptions, escalation paths
- Your answers to approval requests — each one is a data point about how you decide
- Patterns in repeated decisions, surfaced back to you as proposed rules for review
- Your preferred tone and wording, learned from messages you have approved and edited
- Staff fit preferences: who handles which kind of customer, job, or situation
Everything above comes from your business — your records, your rules, your tools. Nothing is invented, and when information is missing, it becomes a question to you rather than a guess.
What this looks like in practice
Every proof item on this site is labeled for exactly what it is.
A repeated discount decision becomes a rule — HVAC
Deptly
Needs your OKThe Maple St customer asked for 10% off a $4,800 AC replacement estimate. Your recorded floor is 5% on installs. Approve 10%, counter at 5%, or hold?
Tue 3:41 PM
Owner
Counter at 5. For repeat customers I'll go to 8 — remember that.
3:52 PM
Deptly
Countered at 5%. Rule drafted from your reply: repeat customers may be offered up to 8% off installs without asking; first-time customers stay at 5%. Approve the rule?
3:53 PM
Owner
Approved.
3:55 PM
Deptly
A repeat customer on Birch Rd asked for a discount on a furnace install — handled at 8% under your rule, estimate updated and sent. No interruption needed.
3 weeks later
- Dinbox
Owner brief
Friday
Your install-discount rule was applied twice this week, both to repeat customers, both logged. One near-miss — a borderline repeat customer — was escalated to you instead.
Where humans stay in the loop
This layer runs inside boundaries, not on its own. Here is who reviews what — and the limits it never crosses.
Human review
- Every rule starts as a proposal you explicitly approve — Deptly never promotes a pattern to a rule on its own.
- You can read, edit, or retire any rule at any time, in plain language.
- Situations that almost match a rule but not quite come to you as questions, not guesses.
- Legal, clinical, safety, coverage, and fiduciary judgments can never be turned into automatic rules — those decisions stay with you or a qualified professional every time.
Guardrails
- Rules apply only within the scope you approved — a discount rule for repeat customers never silently extends to new ones.
- Every rule application is logged, so you can see when, where, and for whom a rule was used.
- Conflicting rules stop the action and escalate — the system never picks a winner on its own.
- A category of decision is excluded from rules entirely: legal positions, clinical judgments, safety calls, coverage determinations, and fiduciary choices.
The full rulebook — control levels, approvals, and audit history — lives on trust and control.
Where this layer shows up
Technology is only interesting when it carries real work. These are the responsibilities this layer powers — and the layers around it.
Responsibilities it powers
The layers around this one
Questions owners ask
Two ways. During onboarding, you state the rules you already know — thresholds, policies, escalation paths — and they are recorded directly. After that, when Deptly notices you answering the same kind of approval the same way repeatedly, it drafts a rule in plain language and proposes it. Nothing takes effect until you approve it.
Yes. The full rule list is readable in plain language at any time — what each rule allows, what its limits are, and when it was last applied. If a rule ever surprises you, that is a defect, not a feature; the design goal is that the list reads like your own policy manual.
No. Rules begin as proposals and take effect only with your explicit approval. Rules also never widen their own scope — a near-miss situation escalates to you rather than stretching the rule, and only your answer can refine it.
Edit it or retire it, effective immediately. Businesses change — prices move, policies tighten, a generous rule gets abused — so rules are meant to be revisited. The weekly brief shows where rules were applied, which is usually how owners notice one drifting out of date.
Final legal, clinical, safety, insurance-coverage, and fiduciary decisions, plus anything contested — a dispute with a customer, a complaint, a quality disagreement. These route to you or a qualified professional every time, regardless of how the situation resembles past ones. No control setting changes that.
It escalates. If the amount is slightly over your threshold or the customer is borderline repeat, Deptly brings you the question with the context and the near-matching rule, rather than deciding the rule probably applies. Your answer can then tighten or extend the rule, if you choose.
It is narrower and more accountable. Generic automation fires whenever its trigger fires, whether or not the situation warrants it. Decision memory encodes your judgment with limits: scoped conditions, logged applications, escalation on near-misses, and a category of decisions it will never touch. The point is not automating decisions — it is making your decisions once instead of fifty times.
Under the hood, then in practice
See what Deptly could take off your plate
Answer a few questions about how your week actually runs and get an honest read on which responsibility this machinery should carry for you first.