Guides
Building Fleet Command: What Online Actually Means
How we repaired a private lab dashboard by separating machine identity, service reachability, fresh telemetry and explicitly authorized controls.
Latest field report · September 2026
Guides
Building Fleet Command: What Online Actually Means
How we repaired a private lab dashboard by separating machine identity, service reachability, fresh telemetry and explicitly authorized controls.
Measured results, reproducible settings, and explicit boundaries between observation and inference.
7Published field reports
14 Sep 2026Newest published report
YesMethodology available
LiveWordPress content source
Published work
From the lab
Published posts are queried from WordPress. New reports enter this layout automatically without duplicating article text on the homepage.
Guides
Versioned agent context: Markdown facts, receipts and a pointer-last handoff
A dated Markdown knowledge system separates facts from plans and history, generates bounded context, and verifies a staged handoff without pretending it trains a model.
Guides
An alive process, an unresponsive agent: the Hermes regex outage
A September 6 recovery traced an unresponsive Hermes backend to one costly approval regex, then repaired its scan behavior without weakening the policy.
Guides
Glimmer Q8 on Two B70s: It Loaded, but Delivered No Code
Sentinel ran a verified Q8 Glimmer instance across two 32GiB B70s. Three neutral one-shot coding tests returned no final code, exposing the gap between load success…
Guides
LM Studio Profiles: Quantization, Context and the Time to a Useful Answer
Lessons from migrating a local agent host to Q8 and a 262,144-token context, including why model identifiers, response limits and latency must be tested separately.
Guides
Romeo: Building a Local AI Workstation Around Two R9700s
Two 32GB GPUs give Romeo room to serve local agents and larger context profiles. Here is the configuration, what changed, and what the evidence actually proves.
Publication standard
Methodology
See how evidence, reruns, claim boundaries, and review status are communicated.
Physical lab
The hardware behind the work
See the multi-vendor systems used for local inference and repeatable field testing.
Evidence before conclusions.
The editorial treatment distinguishes what was measured, what was inferred, what remains planned, and where readers can inspect the reporting standard.
STEP 01
Record
Capture the workload, settings, versions, and observed output.
STEP 02
Repeat
Use consistent conditions and retain individual runs instead of a lone headline number.
STEP 03
Bound
Label observations, inferences, plans, and unresolved checks separately.
STEP 04
Review
Keep staging and publication distinct so evidence can be checked before release.