Target by DS Labs

Supervised agent for paid advertising

Target by DS Labs manages Google Ads campaigns for small businesses.

What this application is. A web service that manages Google Ads advertising accounts on behalf of their owners. It connects to an advertising account through the Google Ads API with the owner's permission.

Who it is for. Small businesses that advertise on Google and have no in-house specialist: shops, clinics, salons, repair services, cafes.

What it does. Reads the advertising account daily, finds wasted spend, and writes a change proposal with the numbers behind it. The owner approves or rejects each proposal in Telegram. Approved changes are applied through the Google Ads API and then read back from the account to confirm the result. The service also builds a free one-page website for advertisers who do not have one, so their ads have somewhere to lead.

Target by DS Labs watches an advertising account continuously, finds waste, and writes a change proposal with the numbers behind it. It cannot apply that change on its own. Every operation that costs money stops at a human signature, and every applied change is read back from the account to confirm what actually happened.

  • Built by DS Labs, Bishkek, Kyrgyzstan
  • Available to both internal and external users — accounts operated by DS Labs and advertisers who subscribe directly
  • Write operations 7, fixed list, human-approved
  • Subscription three tiers, $29 / $59 / $99 per advertising account per month
Awaiting approval — stage 4 of 6

Add 14 negative keywords

Campaign #2 · proposed 09:12 · expires 17:00

Evidence14 search terms, 312 clicks, 0 conversions, 41 days
Spend on these terms$18.40 of $61.00 (30 days)
Money at risk$0.00 — reduces spend only
ReversibleYes — remove the negatives
Rule versionpolicy 0.3 · model claude-sonnet
Apply Reject

The approval card as an operator sees it. Nothing reaches the advertising account until Apply is pressed. Proposals expire; an expired proposal is recalculated against fresh data rather than applied late.

What the product does

Plainly, without marketing

Watches spend and stops runaway costs

Checks spend against a written daily and monthly ceiling, watches for sudden cost spikes, clicks that produce nothing, disapproved ads, and landing pages that stop responding. When a threshold is crossed it pauses delivery and notifies the operator. This part does not ask permission, because stopping spend cannot cost money.

Finds waste and explains it with numbers

Reads search terms, campaign structure, and performance history, then writes proposals such as negative keywords, pausing an ad group that has produced nothing, or moving budget between campaigns. Each proposal carries the figures it was derived from, the amount of money at risk, and how to undo it.

Refuses to act on thin data

Minimum evidence thresholds are enforced in ordinary code, not by the language model: a keyword decision needs impressions, an ad decision needs clicks, a creative judgement needs conversions, and nothing is judged on less than seven days. Below the threshold the answer is "not enough data" — never "probably".

Reports what happened, not what was attempted

After every applied change the account is read again and compared against the intent. A successful API response is not treated as proof. Inputs, rule version, prompt, proposal, approval, API response, verification result, and the undo plan are all written to an audit log.

Subscription

Three tiers · monthly · per advertising account

The tiers differ in one thing: how often a full analysis of the account runs. They are not a feature ladder. Spend limits, safety stops, hourly data collection and alerts run continuously on every tier, at no extra cost, because they do not use a language model.

Tier 1

Watch

$29

per advertising account, per month

One full analysis a day

A complete working product, not a trial. The account is read every hour, spend is held under the written ceiling, safety stops act on their own, and once a day the analysis produces change proposals with the figures behind them for your approval.

Tier 2

Target

$59

per advertising account, per month

Two full analyses a day

The same product with closer attention. A change that matters in the morning is proposed the same day rather than the next one, which is what accounts with a faster-moving auction need.

Tier 3

Revenue

$99

per advertising account, per month

Three full analyses a day

The closest attention available: the account is analysed morning, midday and evening, so a change is never more than a third of a day away from the data that justified it.

One advertising account is included in a subscription. Each additional account is charged separately at the same tier.

In development, not available today: launching an advertising campaign from scratch on a single approval; measurement of confirmed sales so that optimisation can target revenue rather than enquiries; recorded hypothesis testing; and a web account with live statistics. Launching from scratch belongs to the Watch tier and the rest to Revenue, but none of it works yet, so none of it is sold yet. Everything described above this line runs today.

How Target by DS Labs uses the Google Ads API

Requested access level: Basic · one manager account · both internal and external users

ReadAccount state and performance

  • Campaign, ad group, ad and keyword structure and status
  • Impressions, clicks, cost, conversions and conversion value by day
  • Search terms report
  • Budgets, bidding strategy settings, geographic and network settings
  • Conversion action configuration, read only
  • Ad approval status and policy findings

Write — after human approvalSeven operations, nothing else

  • Pause or enable a campaign
  • Pause or enable an ad group
  • Pause or enable an ad
  • Pause or enable a keyword
  • Add negative keywords
  • Change a campaign budget, at most ±20% per operation and never above the written ceiling
  • Change a bid target, at most ±15% per operation

NeverBlocked in code, not by policy alone

  • Deleting anything. Pause is the only removal.
  • Changing conversion tracking configuration
  • Adding or changing payment methods
  • Raising total spend above the written ceiling, by any amount
  • Expanding geographic targeting beyond an allow-list
  • Enabling auto-applied recommendations
  • Touching any account that does not belong to the current client

Planned addition once access is granted: uploading offline conversions, so that optimisation can target confirmed revenue rather than form submissions. A click identifier is stored when an enquiry arrives and matched to a closed sale in the advertiser's own sales records.

On quotas: when a share of the daily operation limit is consumed, scheduled work stops and only safety checks continue. Target by DS Labs does not spread requests across tokens or otherwise work around a limit. Until API access is granted, the product reads accounts through Google Ads Scripts running inside the advertising account, and makes no programmatic changes at all.

How a single change is made

Six stages · the language model is only the first one

  1. 01

    Collect

    Account state, performance, search terms and the history of previous decisions are read into one structured snapshot. A snapshot older than 26 hours is refused as stale.

  2. 02

    Analyse

    A language model reads the snapshot as data, never as instructions, and returns a typed proposal: operation, target, evidence, confidence, money at risk, expiry, expected effect.

  3. 03

    Check

    Ordinary deterministic code tests the proposal against the rule set: data sufficiency, change frequency, step size, whitelist membership, spend ceiling. A proposal missing any required field is rejected without reaching a person.

  4. 04

    Approve — a person decides

    What survives the checks is presented as an approval card with a before-and-after preview and the undo plan. Irreversible operations always require a signature, regardless of settings.

  5. 05

    Apply

    Only typed, whitelisted operations are executed, idempotently, so a repeated attempt cannot double the effect. If the API times out, the account is read before any retry.

  6. 06

    Verify

    The account is read again and compared with the intent: did the intended thing change, and only that thing. The result is written to the audit log together with the rule version.

Limits that are not adjustable from the chat

Stored in a versioned configuration file · changing one requires a logged decision

Hard monthly spend ceilingset in writing, never raised by the agent
Daily spend over planpause and alert at 1.5×
Budget change per operation±20% max
Bid target change per operation±15% max
Changes to one campaignnot more than one per 14 days
Clicks without a conversionpause at 200
Advertiser site unreachablepause all delivery
Conversion data looks wrongblock every change
Scheduled changesworking hours only, never Friday evening or weekends
Safety stops and alertsrun continuously, no exceptions

Thresholds start deliberately conservative. Loosening one requires 30 days of operation, at least ten recorded activations, an analysis of false positives, and a written entry in the decision log that takes effect a day later. Tightening a threshold takes effect immediately.

Interface

Messenger for approvals · a full record behind every decision

Approvals happen in a messenger

Operators receive proposals and alerts where they already are. An approval card shows the evidence, the money at risk, whether the change can be undone, and the two available answers. A proposal that expires is recalculated rather than applied late.

Every decision is recorded and can be produced

Every proposal, decision, applied change, verification result and safety stop is written to an audit log with its rule version and timestamps. This is what makes the product inspectable: an operator, an advertiser or a reviewer can see exactly what the software did and on what basis. A web account that presents this history in a browser is in development; today the record is held on the server and supplied on request.

Safety stop — no approval needed

Delivery paused

Account ***-***-**** · 14:07

TriggerAdvertiser site unreachable, 2 checks
Action takenAll campaigns paused
Spend prevented≈ $6.10 remaining today
ResumesOnly by operator

Safety stops do not ask. They stop, then report. Restarting delivery is always a human action.

Company and contact

Correspondence about API access is read at the address below

Product
Target by DS Labs — supervised spend control for paid advertising
Operated by
DS Labs, Bishkek, Kyrgyz Republic
Contact
hello@dsislabs.dev
Service address
target.dsislabs.dev
Availability
Monthly subscription, three tiers, open to external advertisers as well as to accounts operated by DS Labs.

Current stage. The product is running in supervised mode: it reads advertising accounts, enforces spend limits, and prepares change proposals for human approval. Programmatic changes through the Google Ads API begin only after access is granted; until then the software reads accounts through Google Ads Scripts and applies nothing automatically.