Where Should We Start With AI Agents?
Short answer
Start with one recurring business workflow that has a clear owner, measurable friction, accessible information, and manageable consequences if something goes wrong. Then ask whether it needs an agent that chooses its next steps, or whether simpler automation would work. Test the smallest suitable solution with limited permissions and human oversight before expanding its responsibilities.
The starting pattern
- 01One team
- 02One workflow
- 03One measurable outcome
A useful starting pattern is one team, one workflow, and one measurable outcome.
Start with the problem
Why start with a business problem?
“Deploy an AI agent” describes a technology decision. “Reduce the time required to prepare support cases for review” describes an operational objective.
The second gives your team something to evaluate: the current process, its exceptions, the systems involved, and the result that would justify investment.
Before discussing platforms, document:
- What triggers the work and what counts as completion.
- Who performs it and who owns the outcome.
- Where time, errors, delays, or handoffs accumulate.
- How frequently it occurs.
- What happens when the process fails.
Choose a workflow that matters enough to measure but is narrow enough to understand. An unclear process needs clarification before it needs autonomy.
Agent or automation?
Do you actually need an AI agent?
Complexity ladder
- 01Deterministic automation
- 02Retrieval-based assistant or chatbot
- 03Copilot
- 04AI-assisted workflow
- 05Bounded AI agent
An AI agent uses a model to choose actions and tools as it works toward a goal. An AI-assisted workflow can use the same underlying models while following steps defined in software.
This distinction matters: Anthropic recommends increasing complexity only when needed, recognizing that simpler approaches can be sufficient. Building effective agents
Scroll horizontally to compare all columns.
| What the work requires | Consider first | Example |
|---|---|---|
| Stable rules and predictable inputs | Deterministic automation | Route a request using a required department field |
| Answers from approved information | Retrieval-based assistant or chatbot | Find the current travel policy |
| Drafting while a person directs the work | Copilot | Prepare a response for an employee to edit |
| Language understanding within fixed steps | AI-assisted workflow | Extract document fields, validate them, then request approval |
| Choosing different steps and tools as circumstances change | Bounded AI agent | Investigate a support request across approved systems and propose a resolution |
These categories can overlap. “Chatbot” describes an interface; it does not establish what happens behind it.
Use an agent when adaptive execution adds value. Summarizing text, extracting fields, or answering questions alone does not establish that need.
Choose a use case
How to identify your first AI agent use case
Starting point framework
- 01Candidate workflows
- 02Define the outcome
- 03Check agentic need
Same sequence every time → fixed workflow first
- 04Apply risk gates
Any gate fails → pause the candidate
- 05Score candidates
- 06Pilot candidate
Use the AI Agent Starting Point Framework to compare candidates before committing to a build.
Define the outcome
Write one sentence:
Help the support team prepare account-access cases for review by gathering relevant records and recommending the next step.
Then establish baseline handling time, quality, volume, and exception rates.
Check whether agentic behavior is necessary
Ask: Does the system need to decide what to investigate next based on what it finds?
If every case follows the same sequence, test a fixed workflow first. If the main need is better information access, start with retrieval.
Apply readiness and risk gates
Pause a candidate if:
- No one owns the process or can judge success.
- Required information cannot be accessed appropriately.
- Permissions cannot be restricted to the task.
- Material errors cannot be detected, contained, or reviewed.
- The team cannot support the workflow after launch.
A strong business case does not override these conditions.
Score the remaining candidates
Rate each factor from 1 to 5, with 5 always meaning more favorable for an initial pilot.
Scroll horizontally to compare all columns.
4. Score the remaining candidates Factor What a score of 5 means Business impact Solves a meaningful operational problem Technical feasibility Required behavior is achievable with available capabilities Data readiness Relevant information is accessible, current, and usable Integration simplicity Few, well-supported connections are required Risk manageability Consequences are limited and controls are practical Time-saving potential Substantial repetitive effort could be removed Implementation effort A narrow scope can be delivered with available capacity Measurability Success can be judged against a clear baseline Add the scores for a total out of 40. This equal-weight worksheet helps structure discussion; it does not predict ROI. Business impact covers the broader outcome, while time-saving potential isolates labor effort.
Worked example: three possible starting points
Illustrative scores, not research findings or customer results. Assume all three candidates have passed the initial gates.
Scroll horizontally to compare all columns.
Worked example: three possible starting points Factor Internal policy retrieval Support triage and investigation Invoice exception preparation Business impact 3 4 5 Technical feasibility 5 4 3 Data readiness 4 4 3 Integration simplicity 5 4 2 Risk manageability 4 4 2 Time-saving potential 3 4 4 Implementation effort 5 4 2 Measurability 5 5 5 Total 34/40 33/40 26/40 Policy retrieval may be the best first AI project, yet a retrieval assistant may be sufficient. Support investigation is the stronger agent candidate if each case requires different information-gathering steps. Invoice preparation deserves further investigation but has more integration and control dependencies.
Change the scores using your own evidence. Treat close totals as a reason to inspect assumptions, not as a definitive ranking.
Worked example totals
- Internal policy retrieval34/40
- Support triage and investigation33/40
- Invoice exception preparation26/40
Promising workflows
Which business processes are promising starting points?
The following are candidate patterns, not universal recommendations.
Internal knowledge and employee assistance
Problem
Employees repeatedly search policies and operating guidance.
Pilot
Search approved documents and return answers with source links. Add agentic investigation only if questions require adaptive searches across systems.
Needs
Maintained documents, document owners, and access controls.
Measure
Answer usefulness, factual support, and time to find information.
Main risk and oversight
Outdated or unauthorized information. Preserve user permissions and let employees flag answers for review. Often suitable as a first AI project without an agent.
Customer support triage and IT service desk assistance
Problem
Staff gather context before they can act.
Pilot
Read a ticket, consult approved records, choose relevant diagnostic checks, and draft a recommendation.
Needs
Ticketing data, knowledge articles, and scoped account or asset access.
Measure
Preparation time, routing accuracy, rework, and successful escalation.
Main risk and oversight
Incorrect advice or unintended changes. Have staff approve customer messages, account changes, and access requests. A good agent candidate when investigation paths vary.
Document intake and finance exception preparation
Problem
Staff reconcile inconsistent submissions and chase missing information.
Pilot
Classify documents, extract fields, run coded validations, gather supporting records, and prepare an exception summary.
Needs
Approved storage, document samples, business rules, and relevant records.
Measure
Processing time, extraction quality, and review effort.
Main risk and oversight
Incorrect values reaching financial systems. Keep calculations in deterministic software and require approval before posting or payment. Fixed extraction pipelines may be enough; finance variants need tighter controls.
Sales operations, research, and workflow coordination
Problem
Teams repeatedly assemble briefings, prepare CRM updates, or investigate stalled handoffs.
Pilot
Gather approved information, identify gaps, and draft updates or next actions.
Needs
CRM or task records, approved sources, and named owners.
Measure
Accepted drafts, preparation time, corrections, and handoff delays.
Main risk and oversight
Unsupported claims, incorrect records, or unwanted outreach. Require review before external publication or material updates. Suitable when the information-gathering path varies; fixed reminders need ordinary automation.
Check readiness
What does your organization need before building?
You need enough readiness for the selected workflow, not a complete enterprise AI transformation.
Confirm:
- Business ownershipA process owner, sponsor, and participating users.
- Usable informationRepresentative examples, current source material, and known gaps.
- Integration accessApproved APIs or connectors, test environments, and system owners.
- PermissionsRestricted identities, user access boundaries, and controlled credentials.
- GovernanceDecisions about permitted data use, retention, providers, and relevant obligations.
- Human oversightClear approval points, escalation routes, and backup procedures.
- Operational ownershipPeople responsible for monitoring, incidents, changes, and budget.
Microsoft’s adoption model similarly treats organizational capabilities alongside technology and data. Agentic AI adoption maturity model
Connect systems with controlled interfaces
Prefer supported APIs and connectors. Specify what each tool can read or change, validate its inputs, and record its actions. Design retries so they do not accidentally create duplicate records or transactions.
Enforce authorization in the connected systems or service layer. A prompt telling an agent to respect permissions is insufficient. Google Cloud’s agent identity guidance illustrates the use of distinct agent identities and restricted access. Agent Identity overview
Treat retrieved documents and messages as potentially untrusted input. Test whether misleading content can cause inappropriate tool use or data disclosure.
Start with one agent when an agent is justified
A single agent with a small toolset is a sensible initial architecture to evaluate. Multiple agents can separate specialized responsibilities, but introduce additional coordination, debugging, and operating work.
Add them when testing reveals a specific limitation that separation resolves. OpenAI’s guide discusses both single-agent and multi-agent approaches. Practical guide to building agents
Plan a pilot
How do you launch your first AI agent pilot?
A pilot should produce an investment decision supported by evidence.
Scroll horizontally to compare all columns.
| Phase | Main work | Evidence needed to proceed |
|---|---|---|
| Discover and prioritize | Map the workflow, baseline performance, and select a candidate | Agreed problem, owner, scope, and success criteria |
| Assess readiness | Inspect data, integrations, permissions, and constraints | Feasible access and manageable risks |
| Design and build | Define tools, boundaries, approvals, and fallback behavior | Working bounded solution and representative tests |
| Test and measure | Evaluate outcomes, actions, costs, failures, and user experience | Results against pre-agreed acceptance criteria |
| Deploy and operate | Introduce limited live use, monitoring, support, and change controls | Named owners and evidence supporting continued operation |
A 30/60/90-day plan can be useful as an illustration:
Days 1–30
Establish the baseline, assess readiness, and define the pilot.
Days 31–60
Build and test in a controlled environment.
Days 61–90
Run limited live use if readiness permits, then decide whether to expand.
Data remediation, procurement, integration access, and organizational approvals can extend any phase. Day 90 is not a production guarantee.
Begin with historical cases or shadow mode, where the system proposes actions without executing them. Introduce approved actions only after evaluation.
Your pilot brief should include exclusions, a test set, cost limits, acceptance thresholds, stop conditions, deliverables, and operating ownership. Avoid expanding the scope whenever the demo reveals another possible use.
Measure value
How should you measure success and ROI?
Measure the complete workflow, including review, correction, and recovery.
Scroll horizontally to compare all columns.
| Measure | What to examine |
|---|---|
| Task success | Whether the case reached an acceptable outcome |
| Output quality | Factual support, completeness, and usefulness |
| Action quality | Correct tools, arguments, permissions, and approvals |
| Human effort | Review, corrections, escalations, and exception handling |
| Operational performance | Completion time, failures, retries, and availability |
| Economics | Cost per successfully completed case |
| Adoption | Whether intended users continue using the solution |
Google’s evaluation documentation distinguishes final-response assessment from tool-trajectory assessment. A plausible answer does not establish that execution was correct. Evaluate Gen AI agents
Use representative routine, difficult, and adversarial cases. Repeat tests where behavior varies. Compare with both the current process and a simpler alternative.
For the business case:
Net time released=Baseline human effort−Remaining human effort
Net financial benefit=Attributable financial benefit−Implementation and operating costs
Released capacity is not automatically cash savings. Explain whether it enables more throughput, reduces overtime, avoids hiring, or produces another measurable result. Avoid counting the same benefit twice.
Track severe failures separately from averages. An unauthorized action should trigger investigation even when overall completion rates look strong. No observed incident in a small pilot proves universal safety.
Scale only when the solution meets agreed quality, control, user-value, and cost thresholds. Simplify, redesign, or stop when it does not.
Build, buy, or partner
Should you build, buy, or work with an implementation partner?
Sourcing spectrum
- 01Off-the-shelf agent
- 02Agent development platform
- 03Custom development
Implementation partnerOptions can be combined: an implementation partner can support any point on this spectrum.
Scroll horizontally to compare all columns.
| Approach | Makes sense when | Main trade-off |
|---|---|---|
| Off-the-shelf agent | A standard workflow fits an existing product | Faster setup, with limits on behavior and customization |
| Agent development platform | Your team needs configurable tools, connectors, and deployment capabilities | Less infrastructure work, with platform dependencies and fees |
| Custom development | Important requirements exceed packaged capabilities and your team can maintain the solution | Greater control, with more engineering responsibility |
| Implementation partner | You need delivery expertise or capacity across discovery, integration, evaluation, and rollout | Responsibilities, handover, and support must be contractually clear |
These options can be combined. A partner may configure a platform; an internal team may build custom components around purchased services.
Ask every provider to demonstrate your workflow and difficult cases. Compare integration depth, authorization, evaluation, support, and total operating cost.
What determines implementation cost?
Budget for three categories:
- BuildDiscovery, process design, data preparation, integrations, testing, and user training.
- RunModel and platform usage, hosting, retrieval, monitoring, human review, and support.
- ChangeNew exceptions, updated source material, model changes, connector maintenance, and regression testing.
A useful estimate needs scope, transaction volume, system dependencies, quality requirements, and oversight requirements. Public price ranges cannot establish your project budget.
Reduce avoidable lock-in by clarifying ownership, export rights, platform dependencies, and access to instructions, evaluations, logs, and integrations. Switching providers may still require adaptation and retesting.
How Golabs helps
How Golabs helps businesses start with AI agents
Golabs offers custom AI engineering and implementation support for organizations that need help connecting a business problem to a working solution.
Its services address different needs:
- Tailored AI Agents covers custom agents designed around business workflows, existing systems, and human escalation.
- AI-Orchestrator provides a dedicated human AI expert to assess opportunities and implement initiatives.
- AI Fluency Program supports understanding and practical skills across leaders and teams.
- AI Dedicated Teams provides AI professionals to extend implementation capacity.
The right conversation starts with the workflow: what should improve, what information is available, what actions are permitted, and what evidence would justify further investment.
A packaged solution or internal build may be sufficient. External support becomes useful when expertise, integration complexity, or delivery capacity creates a gap.
FAQs
Frequently asked questions
What should our first AI agent do?
Choose one bounded task with measurable outcomes and manageable consequences. Investigating and preparing support cases for human review is one possible starting point. Validate that it needs adaptive tool use.
Do we need to train our own model?
Not necessarily. First evaluate whether an existing model with appropriate information access and tools meets your requirements. Custom model work needs a specific justification.
Can we start without perfect data?
Yes, if the selected workflow has sufficiently usable information and known limitations. Missing, inaccessible, or unreliable critical information must be addressed or excluded from scope.
Who owns monitoring after the pilot?
Assign ownership before deployment. The business owner tracks outcomes; technical owners manage reliability, access, integrations, and changes. A partner’s responsibilities depend on the agreed engagement.
What happens after a successful pilot?
Expand gradually, continuing evaluation and monitoring. Changes to data, models, and usage can affect performance after deployment. AWS guidance on ongoing evaluation
Your next step
Choose a practical first step
Shortlist three workflows. Name an owner, establish a baseline, and identify the smallest solution worth testing.
If you need help evaluating the use case or its implementation feasibility, bring that workflow to Golabs.