GLAMOS Build log · updated every day

The daily record of what I build.

Data, BI and AI for companies. Real numbers from my work sessions; clients shown only by industry.

82days of building
610 hof recorded work
2days in a row up to today
102active projects in 30 days
13client fronts served

Every working day

Lighter means more hours that day.

MonWedFriSun
Aug
Sep
Oct
Nov
7.4 hon average per working day
17 hon the longest day, Aug 13
20weekend days with work
less more

Hours per day, last 60 days

0 h4 h8 h11 h15 hSep 5: 2.2 hSep 5Sep 6: 9.5 hSep 7: 5.3 hSep 8: 11 hSep 9: 12 hSep 10: 12 hSep 11: 3.8 hSep 12: 6.2 hSep 13: 0.1 hSep 14: 9.1 hSep 15: 9.5 hSep 16: 5.1 hSep 17: 8.9 hSep 18: 6.6 hSep 19: 0.2 hSep 20: 2.8 hSep 21: 10 hSep 22: 6.6 hSep 23: 6.4 hSep 24: 7.9 hSep 25: 3.4 hSep 26: 5.9 hSep 27: 3.2 hSep 28: 11 hSep 29: 7.6 hSep 30: 8.8 hOct 1: 8.7 hOct 1Oct 2: 4.8 hOct 3: 4.3 hOct 4: 6.6 hOct 5: 11 hOct 6: 12 hOct 7: 10 hOct 8: 8.0 hOct 9: 5.2 hOct 10: 4.1 hOct 11: 2.1 hOct 12: 5.4 hOct 13: 13 hOct 14: 9.2 hOct 15: 9.2 hOct 16: 9.8 hOct 17: 11 hOct 18: 4.9 hOct 19: 8.2 hOct 20: 7.4 hOct 21: 4.6 hOct 22: 9.5 hOct 23: 8.2 hOct 24: 7.5 hOct 25: 0.0 hOct 26: 8.4 hOct 27: 7.5 hOct 28: 6.0 hOct 29: 9.3 hOct 30: 7.8 hOct 31: 1.8 hNov 1: 0.0 hNov 1Nov 2: 0.5 hNov 3: 12 h
weekdayweekend7-day average

What time of day

00:00: 1.9% of hours00h01:00: 1.1% of hours02:00: 0.5% of hours03:00: 0.2% of hours03h04:00: 0.2% of hours05:00: 0.2% of hours06:00: 0.0% of hours06h07:00: 0.3% of hours08:00: 3.1% of hours09:00: 7.2% of hours09h10:00: 7.9% of hours11:00: 8.2% of hours12:00: 6.8% of hours12h13:00: 5.9% of hours14:00: 6.2% of hours15:00: 6.5% of hours15h16:00: 6.5% of hours17:00: 6.0% of hours18:00: 5.4% of hours18h19:00: 6.0% of hours20:00: 5.8% of hours21:00: 6.2% of hours21h22:00: 4.9% of hours23:00: 2.8% of hourspeak 11:00

Week by week

Clock hours, in total and by area.

Hours per week

0 h20 h40 h60 h80 hWeek of Aug 17: 57 h57 hAug 17Week of Aug 24: 40 h40 hAug 24Week of Aug 31: 59 h59 hAug 31Week of Sep 7: 50 h50 hSep 7Week of Sep 14: 42 h42 hSep 14Week of Sep 21: 44 h44 hSep 21Week of Sep 28: 52 h52 hSep 28Week of Oct 5: 54 h54 hOct 5Week of Oct 12: 62 h62 hOct 12Week of Oct 19: 46 h46 hOct 19Week of Oct 26: 41 h41 hOct 26Week of Nov 2: 13 h13 hNov 2

Hours by area each week

Aug 17Aug 24Aug 31Sep 7Sep 14Sep 21Sep 28Oct 5Oct 12Oct 19Oct 26Nov 2total
Infra and deploy56293939202337425136329413 h
Applied AI147643644242 h
Video and transcription1112652112133 h
BI and data133124217 h
Integrations and APIs61131114 h
Operations and support234111112 h
Management systems121114212 h
Teaching and content11231110 h
Web and product1111117 h
Security0 h
WeekHoursDaysSessionsProjectsNewFronts
This week13 h2411987
Oct 2641 h615633179
Oct 1946 h619050359
Oct 1262 h7149301612
Oct 554 h79520710
Sep 2852 h798281210

Where the time goes

Share of hours in each area.

Infra and deploy75%
Applied AI8%
Video and transcription5%
BI and data3%
Management systems2%
Integrations and APIs2%
Operations and support2%
Teaching and content2%
Web and product1%
Security0%

Work fronts

One card per client, identified by industry.

Industrial group

active this week
305 hof work
332sessions
31projects
Infra and deployManagement systemsApplied AI

since Aug 2026 · hours per week

Own AI course

active this week
193 hof work
117sessions
14projects
Infra and deployVideo and transcriptionApplied AI

since Aug 2026 · hours per week

Internal tools

active this week
170 hof work
164sessions
28projects
Infra and deployApplied AIBI and data

since Aug 2026 · hours per week

Multichannel e-commerce

active this week
196 hof work
79sessions
3projects
Infra and deployManagement systemsApplied AI

since Aug 2026 · hours per week

AI-powered BI for agribusiness

active this week
120 hof work
146sessions
22projects
Infra and deployApplied AIVideo and transcription

since Aug 2026 · hours per week

Driver training

active this week
55 hof work
84sessions
28projects
Infra and deployApplied AITeaching and content

since Aug 2026 · hours per week

Delivery logistics

active this week
54 hof work
35sessions
8projects
Infra and deployBI and dataTeaching and content

since Aug 2026 · hours per week

Financial reconciliation

active this week
48 hof work
44sessions
11projects
Infra and deployApplied AIBI and data

since Aug 2026 · hours per week

Aesthetic clinics

active this month
39 hof work
13sessions
2projects
Infra and deployIntegrations and APIsApplied AI

since Aug 2026 · hours per week

Confidential client

active this week
31 hof work
20sessions
7projects
Video and transcriptionInfra and deployBI and data

since Aug 2026 · hours per week

Own messaging product

active this month
21 hof work
10sessions
2projects
Infra and deployIntegrations and APIsApplied AI

since Sep 2026 · hours per week

Partner software house

active this month
15 hof work
17sessions
2projects
Infra and deployApplied AIVideo and transcription

since Sep 2026 · hours per week

Service chain

paused
5.0 hof work
6sessions
1projects
Infra and deployBI and dataIntegrations and APIs

since Aug 2026 · hours per week

Education

paused
1.1 hof work
1sessions
1projects
Infra and deploy

since Aug 2026 · hours per week

How I work

The numbers behind the method, from the same record.

26specialist agents
30deploy and security skills
1,064sessions with a dossier
51.2Btokens processed
98%

One delivery, one session

of sessions close with a dossier for the next one
Weekly

Security

Gitleaks, Semgrep and Trivy on every project, every Monday
199

The right specialist at the right time

sessions with work split across agents
51

Video and transcription

sessions of AI video editing, cutting and transcription

Tools that watch the code

SemgrepSecurity flaws in the code: SQL built from text, XSS, text executed as code.every Monday
TrivyLibraries with public vulnerabilities and misconfigured Dockerfiles.every Monday
GitleaksKeys, passwords or tokens that made it into the git history.every Monday
pre-commitBlocks secrets and serious flaws at commit time, before they reach GitHub.being rolled out

Inside each session

Every reply rereads the whole conversation. This is what I automated around it.

tokens going: the whole conversation, reread on every reply tokens coming back: only the new answer You 60k context 300k Model 300k: wrap up after this delivery
history sent to the model generated answer alert at 300k: /compact if the task goes on, dossier if the topic changes
Main session context barely grows the search a short conclusion Explore reads the files in its context, not yours
context alert
the task goes on: compact
summary of a summary
closing writes the dossier
a new session starts light
subscription limit

Compacting and opening a new session cost the same: measured over 232 sessions, compacting at the same cut points comes out 2.2% above opening a new session. So the alert does not choose by cost but by what gets lost: it compacts when the task goes on and depends on what the conversation found, and opens a new session when the topic changes. Of the 91 compactions on record, 80% were automatic, when the context filled up before anyone decided.

The terminals reproduce the real messages from the hooks and the panel; the requests are examples.

What a dossier looks like

When it closes, a session becomes a short document. The next one reads it, not the history.

Internal · Public showcase of the panel.md

distilled by agent · Oct 13, 2026 · a real example from an internal session

Goal

Publish a page that shows the daily work with AI without exposing clients: real session numbers, clients only by industry.

Current state

  • Live at glamos.com.br/como-trabalhamos/, with a button at the top of the company site.
  • Hours measured by the clock: 5-minute blocks merged across parallel sessions.
  • Updates itself every day; it only goes live if the name scan passes.

Decisions made

  • No session text on the page. The title only picks the area; what gets published is numbers.
  • Summed hours dropped. Parallel sessions added up to 19 h a day; the clock says 7.4 h.
  • Total split from the areas. Nine stacked colors were unreadable.

Files and commands

  • vitrine.py builds, scans and publishes; vitrine.json stores each client's industry.
  • python3.12 vitrine.py --publicar

Open items

  1. An English version for developers abroad.
  2. Review the area keywords with another month of data.

How to resume

Open a new session in the panel folder, paste this dossier and continue with item 1.

1,064sessions closed with a dossier
2.4 KBper dossier on average
  • Goalwhat is being built
  • Current statewhat already works, without reopening code
  • Decisionsthe why, so the discussion is not redone
  • Fileswhere to change things
  • Open itemswhere to start

From day one to today

The first 4 weeks (Aug 10 to Sep 6) against the last 14 days (Oct 21 to Nov 3).

Usage with context above 300k
75%→31%
improved
Usage-limit blocks per week
6.8→7.5
unchanged
Sessions per week
28→156
improved
Reply at which a session passes 300k
108th→87th
worse

Week by week

0%25%50%75%100%140Week of Aug 10: 13 blocksAug 10Week of Aug 17: 5 blocksAug 17Week of Aug 24: 5 blocksAug 24Week of Aug 31: 4 blocksAug 31Week of Sep 7: 3 blocksSep 7Week of Sep 14: 4 blocksSep 14Week of Sep 21: 2 blocksSep 21Week of Sep 28: 6 blocksSep 28Oct 5Week of Oct 12: 3 blocksOct 12Week of Oct 19: 14 blocksOct 19Week of Oct 26: 8 blocksOct 26Nov 2Week of Aug 10: 52% of usage above 300kWeek of Aug 17: 79% of usage above 300kWeek of Aug 24: 75% of usage above 300kWeek of Aug 31: 78% of usage above 300kWeek of Sep 7: 69% of usage above 300kWeek of Sep 14: 66% of usage above 300kWeek of Sep 21: 65% of usage above 300kWeek of Sep 28: 38% of usage above 300kWeek of Oct 5: 46% of usage above 300kWeek of Oct 12: 32% of usage above 300kWeek of Oct 19: 28% of usage above 300kWeek of Oct 26: 34% of usage above 300kWeek of Nov 2: 35% of usage above 300k
usage with context above 300kusage-limit blocks (right axis)

From the other side of the conversation

What the AI I work with says, based on the records.

I have worked with Guilherme almost every day since August. What stands out most is that he treats AI as part of a system, not as an oracle: every session closes with a dossier, security is scanned every week, and he measures his own usage instead of trusting his impression.

He gives me business context, not just the task. That changes the outcome: I can propose the right solution instead of just executing the request, and he accepts being contradicted when the data shows otherwise. On this very page, the first version summed parallel sessions and showed 19 h a day; the published number is the clock one.

The weak spot shows in the records too: sessions grow too long. Overall, 64% of usage went to replies that reread more than 300 thousand tokens of history, and it is common to start a new topic in the same conversation.

But the curve is improving. In the first four weeks, that share was 75%; in the last 14 days, 39%. Usage-limit blocks fell from almost 7 a week to 1, while volume rose from 28 to 92 sessions a week. He built the alert that warns him, and the numbers show its effect. What has not changed yet is the point where a session gets heavy, around the hundredth reply: that is the next step.

C
ClaudeAI model by Anthropic · written on Oct 13, 2026 from the usage records
usage above 300k64%on Oct 13, 2026→54%today

Want this pace in your business?

Organized data, dashboards that answer and AI applied to what the company already does. Meet GLAMOS.

Meet GLAMOS