Skip to main content

Building Effective Agents (and Teams of Agents)

Building a great Gobii agent starts with a clear goal and a well-defined scope. Whether you're creating a single research assistant or a team of specialized agents that pass work between each other, the same principles apply: give agents focused instructions, the right tools, and clear boundaries.

Designing a Single Agent​

Start with a Clear Purpose​

Every agent should have one primary job. Instead of creating a single agent that tries to "handle everything," create focused agents:

❌ Too Broad✅ Focused
"Monitor competitors and send reports and also manage billing""Monitor competitor pricing changes and alert when prices drop"
"Research topics and reply to customer emails and track shipments""Research industry trends and compile weekly briefings"

When an agent has too broad of a scope, it uses more credits on context switching, makes more mistakes, and is harder to debug.

Write Great Instructions​

Your agent's instructions (its system prompt) are the most important factor in its performance.

Do:

  • Use clear, direct language: "Send a daily summary of trending topics to the team Slack channel."
  • Include specific output formats: "Format results as a Markdown table with columns: Topic, Source, Relevance."
  • Set boundaries: "Only research topics related to artificial intelligence and machine learning."
  • Describe edge cases: "If no new results are found, skip today's report — don't send an empty message."

Don't:

  • Use vague language: "Keep me updated on stuff."
  • Give multiple unrelated responsibilities.
  • Forget to specify what not to do.

Set the Right Intelligence Level​

Gobii offers five intelligence tiers that directly affect credit consumption:

TierMultiplierPer-Task Cost (0.15 base)Best For
Standard1×0.15 creditsSimple lookups, monitoring, routine data collection
Premium2×0.30 creditsResearch synthesis, multi-step analysis
Max3×0.45 creditsComplex reasoning, code review, detailed reports
Ultra8×1.20 creditsDeep analysis, large-context tasks
Ultra Max15×2.25 creditsMaximum reasoning, complex multi-step agent coordination

Use the Standard tier for scheduled monitoring tasks and simple data gathering. Reserve Ultra and Ultra Max for complex, one-off analysis where deep reasoning matters.

Set a Daily Credit Budget​

Every agent has a configurable daily soft limit. Gobii aims to stay within this budget and only slightly exceeds it when the agent is near completion of a task. A hard limit (derived from your soft limit — 2× by default) stops the agent entirely for the day.

  • Start low — give new agents a conservative budget (e.g., 10–20 credits/day)
  • Monitor usage — check the Usage dashboard to see actual consumption
  • Adjust up — increase the budget only when you see the agent hitting its limit productively

Building Teams of Agents​

When your workflow involves multiple steps or domains, consider splitting work across several specialized agents connected via peer linking.

When to Use Multiple Agents​

Use a Single Agent When...Use Multiple Agents When...
The task is straightforward and linearWork spans distinct domains (e.g., research → drafting → review)
A single instruction set covers everythingEach step needs different tools or permissions
You want the simplest possible setupYou need parallel work streams
Latency isn't criticalEach subtask is deep enough to justify its own agent

The Research → Draft → Review Pattern​

A common multi-agent setup follows a pipeline:

┌────────────┐     ┌────────────┐     ┌────────────┐
│  Research  │ ──▶ │   Writer   │ ──▶ │  Reviewer  │
│  Agent     │     │  Agent     │     │  Agent     │
│            │     │            │     │            │
│ Gathers    │     │ Synthesizes│     │ Fact-      │
│ sources &  │     │ findings   │     │ checks &   │
│ data       │     │ into draft │     │ edits      │
└────────────┘     └────────────┘     └────────────┘

Each agent has:

  • A focused instruction set
  • Different tools (research uses web search; writer uses email/docs)
  • A peer link to pass results to the next agent in the chain

Design Your Agent Team​

  1. Map the workflow — List the distinct steps from start to finish
  2. Assign one agent per step — Each agent owns one responsibility
  3. Define handoffs — What does each agent pass to the next? (e.g., "After researching, send a summary to the Writer agent")
  4. Set the trigger — Usually the first agent runs on a schedule; downstream agents run when they receive input from the previous agent
  5. Test the chain — Start with a manual trigger and verify each link before enabling the full schedule

Avoid Common Pitfalls​

  • Circular workflows — Don't create a loop where Agent A passes work to Agent B, which passes work back to Agent A. This burns credits without progress.
  • Overlapping schedules — If two agents independently monitor the same source, they'll duplicate work. Assign clear boundaries.
  • Competing for contacts — When multiple agents share a contact (e.g., all sending to the same Slack channel), use templates to ensure consistent formatting and avoid conflicting messages.

Using Templates for Consistency​

Gobii's template library lets you create reusable agent configurations. Templates are especially useful for teams:

  • Standardize agent patterns — Create a "Research Agent" template that anyone in your org can instantiate
  • Share across workspaces — Publish templates so teams maintain consistent agent designs
  • Iterate on proven setups — When you find a great agent configuration, save it as a template

Next Steps​