Somnio Software Logo
What We Do
Services
Managed Product DeliveryCo-Managed Delivery TeamsStaff Augmentation
Product Solutions
Product Strategy & DesignCustom Software DevelopmentAI EnablementProduct Scaling & EvolutionProduct Security & ComplianceIndustry Solutions
Capabilities
Product StrategyProduct DefinitionProduct DesignProduct GrowthFlutter DevelopmentMobile DevelopmentWeb DevelopmentBackend DevelopmentQA AutomationDevOps & CloudAI EngineeringData & AnalyticsSecurity EngineeringProduct MaintenanceIT Recruiting ServicesPrivate Equity
Explore everything we do →
Flutter
Flutter
Flutter EverywhereMigration & ModernizationGenUIFlutter Expertise
Explore Flutter →
AI
AI
AI Consulting & StrategyAI in ProductAI Agents & AutomationGenerative AI Solutions
Explore AI →
Our Work
Our Work
IndustriesSuccess Cases
Resources
Resources
Somnio SolutionsOpen SourceTutorials & TalksDownloadablesThe CTO Lounge
Explore resources →
About
About
CompanyPress & NewsCareers
Blog
Let’s talk

Introducing Beacon: AI monitoring for teams in production

Stop guessing what your AI seats produce. Beacon's AI monitoring shows leaders their AI costs, 5-hour usage limits, agent adoption, and shipped work.

Introducing Beacon: AI monitoring for teams in production
Authors
Gerardo Castillo
Gerardo Castillo
Flutter Developer
Technical
N
min read
/
November 17, 2026
Share
Copy post url
linkedin
Facebook
Twitter

Table of Contents

Example H2

Beacon is the AI monitoring platform we built to see what our AI seats cost, where people get blocked, and what actually ships. Here is how it works and what changed at Somnio.

Many engineering teams have seen their AI bill double from one month to the next, and the same questions follow: should we upgrade seats or cancel unused licenses, and is all that spending helping the team ship faster?

A monthly invoice or a server dashboard can't answer that. It shows a single dollar total, not the developer blocked by a usage cap, the paid seat nobody used, or the contractor logging in with a personal email.

Giving your team access to AI tools takes an afternoon. Knowing whether those tools are worth the investment is where companies hit a wall.

‍

Enter Beacon: AI monitoring

At Somnio Software, we help companies move beyond simply buying AI tools to redesigning how their teams build software. As our own squads and our partners scaled their daily use of Claude Code, Claude Cowork, and AI agents, we ran into a clear problem: you cannot manage an AI-driven team if you can't see what it is doing.

Standard monitoring tools were built for system administrators debugging servers, not for leaders managing teams and budgets. When we dug into our own logs to answer simple questions like "Which department is getting the most value from their AI seats, and who keeps hitting usage limits?", we found three recurring blind spots:

  • Spend and workflows were disconnected from shipped work: Raw token charts were misleading because over 95% of reported tokens were background cache reads rather than billable usage, and there was no simple way to see which AI workflows (models, skills, and subagents) were actually helping teams ship code.
  • Usage limits were silently stalling developers: Engineers were hitting 5-hour usage caps and getting blocked mid-afternoon without opening tickets, leaving us guessing who needed a seat upgrade and who was fine on a Standard plan.
  • Unusual spend and idle seats were buried in logs: Spend spikes, weak cache use, and paid seats that people had quietly stopped using were hidden inside technical telemetry where no manager would spot them in time.

We built Beacon to solve this.

Beacon is an AI monitoring and management platform built for CTOs, VPs of Engineering, Product Leaders, and technical managers. Instead of forcing you to read technical logs, Beacon shows you what matters at a glance: what your AI tools cost, where your people are getting blocked, how they are using AI agents, and what real work is coming out the other side.

‍

Beacon Overview: total tokens and estimated cost, billable tokens over time, active people, cache hit rate and month projection
The Overview board: total tokens and their estimated cost, billable tokens over time, active people, cache hit rate, and the month's projection. (Screenshots in this post use sample data to protect individual privacy; our real production numbers from Somnio are shared below.)

Three core problems Beacon solves

1. Connecting AI spend to real shipped work

Most AI dashboards only tell you how much people consume. Knowing that Developer A used 12 million tokens and Developer B used 4 million doesn't help you make a decision. Did Developer A spend all afternoon fighting with a bad prompt, or did they use AI agents to finish six pull requests?

On top of that, standard token counters mix background memory reuse with the tokens you actually pay for, making raw usage numbers look over twenty times larger than what impacts your bill.

Beacon keeps billable usage apart from background caching automatically: the Overview charts billable tokens over time next to the total and shows the cache hit rate. Its Usage vs. Outcome view then puts estimated cost right next to what each person and team delivered:

  • Real delivery metrics: Track commits, pull requests, lines added, tokens per commit, and estimated Cost per Commit.
  • Cost × outcome map: Place each person by tokens and by commits plus pull requests, so heavy use with little outcome stands apart from heavy use that ships.
  • Workflow and agent adoption: See each person's model mix (Opus, Sonnet, or Haiku) in Token usage and efficiency. In Habits, see how many people delegate to Subagents, adopt Skills, and run parallel sessions, plus which connectors, skills, and plugins the team extends Claude with.

‍

Usage vs. Outcome: tokens, commits, pull requests, tokens per commit and lines per million tokens, with a cost × outcome map per person
Usage vs. Outcome: tokens and estimated cost next to commits, pull requests, tokens per commit and lines added, with each person placed on a cost × outcome map.
Habits: subagent share, skill adoption, parallel sessions, mastery levels, work styles and good practices across the organization
Habits: how the organization works with AI, from subagent share and skill adoption to the good practices people follow.
Connectors, skills and installed plugins by number of people, and who triggers the skills
What the team extends Claude with: connectors, skills and plugins by number of people, and whether skills are triggered on request or by Claude on its own.

The purpose of these views is to help the whole team improve, not to evaluate developers by line counts. Instead of guessing whether high AI usage means high productivity, you can see which practices your team has and which get more done with the same tokens, and share them with everyone else.

2. Catching usage caps before momentum stalls

AI plans don't just have monthly budgets; they have short-term usage caps (often measured in 5-hour windows). When a developer hits that ceiling in the middle of a complex task, the tool slows down or locks them out completely.

Most developers won't open a support ticket to tell you they were blocked. They just lose their train of thought and wait. At the same time, managers have no easy way to know who needs a Premium seat and who is fine on a Standard seat.

Beacon's Plan capacity view shows you how your team interacts with their plan boundaries:

  • Slowdowns vs. hard blocks: Beacon distinguishes between a brief rate limit and a Hard Block, where the AI tool fails completely and stops a developer from working, person by person and day by day.
  • The likely cause per person: The most blocked people come first, each with a likely cause (heavy use, many sessions at once, or hitting the limit without much use) and what to do next.
  • 5-hour peak per person: Each person's peak billable usage appears as a share of the limit, against comfortable, close, and at the limit zones.
  • Right-sizing seats: The seat table recommends, person by person, whether to upgrade, keep the seat, or review usage, and a seat scenario shows what the recommended upgrades would cost per month.
Plan capacity: people with friction, days at the limit, hard blocks, 5-hour peak and upgrade candidates, with the likely cause per person and each person's 5-hour window
Plan capacity: who hits the limit and why, next to each person's 5-hour peak as a share of the limit.
Limits and hard blocks by person and day, with a seat recommendation per person and a monthly seat scenario
Limit errors and hard blocks by person and day, a seat recommendation for each person, and what the recommended upgrades would cost.

3. Replacing technical logs with plain-English cases to review

Nobody wants to dig through four different charts every morning just to find out if something went wrong yesterday, and noisy Slack alerts quickly get muted.

Beacon's Usage anomalies screen brings the unusual cases together in one place, written in plain English, each with what happened, the evidence, and what to do:

  • Expensive per token: People who pay more per million tokens than their peers, with the money at stake.
  • Low cache use: People whose cache use falls below the target, with a concrete way to improve it.
  • Spend jumps: A day or a week far above someone's usual spend, so you can confirm whether it was expected work or a mistake.
  • Stopped using Claude: People who used Claude regularly and then stopped, so you can reassign idle licenses or check if someone is stuck.

Blocked team members and people who keep hitting their limit are covered in Plan capacity above, and outside accounts in Approved Domains & Access Control below.

Usage anomalies: people with anomalies, money at stake, cases to review and who stopped using Claude
Usage anomalies: each case says what happened and what to do, followed by who stopped using Claude.

On Monday morning, a manager can see who is spending out of the ordinary, who stopped using their license, and what to do about each case.

What happened when we rolled out Beacon at Somnio

Screenshots with sample data show how the interface works, but the real test of any monitoring tool is whether it changes how a team operates.

We compared our own engineering team's Claude Code usage at Somnio Software across the four weeks before Beacon's first production release against our most recent 30 days in production. Instead of cutting AI spend, visibility helped us expand adoption, share the workflows of our most effective engineers, and get far more shipped work out of every dollar:

Metric (Claude Code) Before Beacon (4-week baseline) With Beacon (Latest 30 days) Change
Active people per week 20 to 35 47 to 50 Strong adoption growth
Pull requests per week 38 446 12x
Commits per week 87 2,257 26x
Estimated weekly spend $3,774 $15,128 4x
Cost per PR $101 $34 -66%
Cost per commit $43 $6.70 -85%
Lines added per commit 1,035 239 -77%
Lines added per dollar 23.9 35.7 +49%
Lines added per million tokens 13.7 12.9 -6%
Cost per million tokens $0.57 $0.36 -37%

Beacon was not the only thing that changed in those weeks: the team grew and adopted new ways of working with AI. What Beacon changed is that we could see those shifts as they happened and spread the ones that worked.

Three takeaways stood out from our own rollout:

  • Output scaled 3x faster than spend: While weekly AI spend grew 4x as nearly the entire team became active every week (from 20-35 up to 47-50 people), weekly pull requests grew 12x and weekly commits grew 26x.
  • Smaller, cleaner changes at a fraction of the cost: Average lines added per commit dropped by 77% (from 1,035 down to 239 lines). Instead of giant, risky code dumps, developers shifted to smaller, incremental commits and pull requests, bringing our cost per commit down 85% (from $43 to $6.70) and cost per PR down 66% (from $101 to $34).
  • Better token efficiency across the board: By spotting low cache hit rates and helping the team pick the right model mix and subagent workflows for each task, our cost per million tokens dropped 37% ($0.57 to $0.36) and lines added per dollar rose 49% (23.9 to 35.7).

Built for fast setup, team governance, and privacy by design

Beyond daily usage and delivery metrics, Beacon connects to your existing workflow in minutes and keeps growing organizations organized without adding administrative overhead:

  • No-friction setup: Beacon reads standard OpenTelemetry events from Claude Code and agent workflows alongside repository activity (commits and pull requests), without changing how developers work in their terminal or IDE.
  • Zero prompts or code recorded: Developers often hesitate to adopt monitoring tools out of fear that someone will read their prompts, while security teams worry about leaked secrets or passwords being stored in logs. Beacon tracks operational activity only and never records prompt text or source code.
  • Department views: Follow each department against its token goal, its own past, and fixed efficiency targets, with adoption shown per team. When someone changes squads, their reporting updates automatically.
  • Approved domains and access control: Manage approved company email domains and accounts from one place so unauthorized accounts are flagged and separated before they skew your company totals.
Departments: each team's tokens, estimated cost, goal and efficiency targets, with adoption by department
Departments: each team against its goal and efficiency targets, with adoption by department.
Allowed domains and accounts: telemetry is only accepted from the listed domains and accounts
Approved domains and accounts: manage the list from one place.
Denied accounts: an outside account with its attempts, status and the option to allow it
Denied accounts: every outside account, how often it tried, and its status.Type image caption here (optional)

Why visibility separates AI demos from real products

Every company today can buy the same AI licenses and access the same models. Buying the tool is no longer a competitive advantage.

As we shared recently in our post on Leading AI Transformation: Why Companies Must Move Beyond Tools, the companies that pull ahead are the ones that adapt how they work, measure real adoption, and connect AI usage to real results. Handing out a hundred AI seats without visibility is just adding another software bill. Knowing how those tools help your people ship faster, where your team is hitting walls, and what every dollar of AI spend produces is how you build an AI-native organization.

When the monthly AI invoice arrives, it shouldn't trigger a guessing game. You should already know which seats to upgrade, which idle licenses to reassign, who got blocked by a usage cap, which outside accounts tried to log in, and how your AI spend translated into shipped work. We built Beacon to give our own teams and our partners those answers every day, long before the monthly bill lands.

Frequently asked questions about AI monitoring

What is AI monitoring for engineering teams?

AI monitoring is the practice of tracking how a team uses AI coding tools and agents: what they cost, where people get blocked by usage limits, which workflows they adopt, and what work comes out of them. Unlike server monitoring, it is built for the leaders who manage budgets and teams, not for system administrators.

‍How does Beacon track Claude Code usage?

Beacon reads the standard OpenTelemetry events that Claude Code and agent workflows already emit, and combines them with repository activity such as commits and pull requests. Setup takes minutes and does not change how developers work in their terminal or IDE.

What are Claude Code 5-hour usage limits?

Besides monthly budgets, Claude plans have short-term usage caps measured in 5-hour windows. When a developer reaches the cap in the middle of a task, the tool slows down or stops responding until the window resets. Beacon shows each person's 5-hour peak as a share of the limit, so managers know who needs a different seat.

Does Beacon record prompts or source code?

No. Beacon tracks operational activity only, such as tokens, estimated cost, sessions, limit errors, commits, and pull requests. It never records prompt text or source code, which helps developers trust the tool and keeps secrets and passwords out of the logs.

Ready to stop flying blind on your team's AI usage?

If you are scaling Claude Code, Claude Cowork, or AI agents across your organization and want clear visibility into costs, usage limits, and team outcomes, reach out to our team at Somnio Software to book a live demo of Beacon.

Contact us

Stay in the loop!

Receive tech news, software tips, and business insights.
Subscribe to our newsletter!

Thank you! Your submission has been received!
Oops! Something went wrong.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Read next

Technical

A2UI 1.0 at Flutter Create: Somnio's fintech agent demo

Read more
A2UI 1.0 at Flutter Create: Somnio's fintech agent demo
Read more
Technical

iPhone Duo and Flutter: What the foldable iPhone changes

Read more
iPhone Duo and Flutter: What the foldable iPhone changes
Read more
Somnio Software Logo
Services
Managed Product DeliveryProduct Strategy & DesignStaff AugmentationWhat We DoAll services
Our work
IndustriesFintechHealthcareEducationEntertainmentSuccess Cases
About
CompanyFlutter ExpertiseCareersPress & NewsPrivacy PolicyCompany Presentation Brochure
Resources
Open SourceTutorials & TalksDownloadablesBlogThe CTO Lounge Episodes
Office
José Ellauri 1142
Montevideo, Uruguay
11300
Contact
hello@somniosoftware.comjobs@somniosoftware.com
+1 305-203-1734 - US
Clutch Award Top B2B Company 2022
Clutch Award Top B2B Company 2022Clutch Award Top B2B Company 2022Clutch Award Top B2B Company 2022Clutch Award Top B2B Company 2022Clutch Award Top B2B Company 2023Clutch Award Top B2B Company 2023Clutch Award Top B2B Company 2023Clutch Award Top B2B Company 2023Clutch Award Top B2B Company 2022The Manifest Award Top Flutter Developers 2021Clutch Award Top 1000 Companies Global 2022Clutch Award Top B2B Company 2023