This video argues that Hermes Agent is best used not as a replacement for Claude or Codex in building apps, but as an always-on operator/AI employee, and walks through 15 concrete business roles for it (SEO analyst, lead scraper, sales CRM, research agent, content producer, investment analyst, advisory council, etc.).
Nemanja Mirkovic12 minTranscript found
Quick learning frame
Read this before watching.
Agent ops treats agents like services: observable state, queues, permissions, logs, recovery, and post-run review.
New playlist item from Nemanja Mirkovic; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to scope agent work correctly by assigning Hermes the operating-and-monitoring jobs while reserving Claude/Codex for building tools, then mapping those operator roles onto real bottlenecks in your own business.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Project state
02Session
03Queue/Kanban
04Tools
05Logs
06Recovery
07Post-run review
Deep lesson
Turn this video into working knowledge.
1,847 cleaned transcript words reviewed across 584 timed caption segments.
Thesis
15 Hermes Agent use cases I wish I tried sooner teaches a practical hermes operations move: This video argues that Hermes Agent is best used not as a replacement for Claude or Codex in building apps, but as an always-on operator/AI employee, and walks through 15 concrete business roles for it (SEO analyst, lead scraper, sales CRM, research agent, content producer, investment analyst, advisory council, etc.).
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:12
Build vs. operate split
“wanted Hermes Agent to replace those two so that they can build apps, build systems, build content inside of Hermes and not touch Claude or Codex anymore other than the models from them. And it absolutely can do...”
The creator's core reframe: Hermes is slower and less token-efficient than Claude or Codex at building apps and systems, so the durable pattern is to build a CLI or tool with Codex and then let Hermes operate it (e.g. the Press Wiz backlink-ordering CLI is built in Codex but driven by Hermes). List the recurring tools you use, then label each as 'build with Codex/Claude' or 'operate with an agent' to find which jobs actually fit an operator agent.
5:34
Self-improving research agent
“and I sent it to my agent, and we worked out an idea for this video, how we can create this. So, it it adjusts the sources, and it creates the package or outline or scripts, whatever you...”
A daily research agent that follows your chosen sources (X, YouTube, Claude/Codex news) and sends one digest replaces hour-long doom-scrolling, and rating its output makes it surface better-targeted results the next day, so feedback is the mechanism that tunes relevance over time. Sketch a daily-digest agent for your own interests and define an explicit rating step so the relevance loop actually improves rather than staying static.
9:12
Investment analyst pattern
“over. And yeah, it said that Microsoft is the best. I'm not going to argue with this. It's just one example how you can use this agent. It also has my portfolio tracker that I created with Cloud...”
The investment-analyst agent ('Warren') takes a stock list, crawls preferred sources with Firecrawl for up-to-date data, returns aggregated advice, and logs trades into a Claude/Codex-built portfolio tracker from a screenshot, showing how an operator agent layers on top of a custom-built tool with options tracking the off-the-shelf trackers lacked. Pick one data-gathering task you do manually and design an agent that pulls from your named sources and writes results into a tool you build separately.
01
Project state
Start with this video's job: This video argues that Hermes Agent is best used not as a replacement for Claude or Codex in building apps, but as an always-on operator/AI employee, and walks through 15 concrete business roles for it (SEO analyst, lead scraper, sales CRM, research agent, content producer, investment analyst, advisory council, etc.). Treat "Project state" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:12, where the video says: “wanted Hermes Agent to replace those two so that they can build apps, build systems, build content inside of Hermes and not touch Claude or Codex anymore other than the models from them. And it absolutely can do...”
02
Session
Use "Session" to locate the part of the hermes operations mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 5:34, where the video says: “and I sent it to my agent, and we worked out an idea for this video, how we can create this. So, it it adjusts the sources, and it creates the package or outline or scripts, whatever you...”
03
Queue/Kanban
Turn "Queue/Kanban" into the reusable artifact for this lesson: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria. This is where watching becomes something you can inspect and reuse.
04
Tools
Use "Tools" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Logs
Use "Logs" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Recovery
Use "Recovery" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
07
Post-run review
Connect "Post-run review" to 15 Hermes Agent use cases I wish I tried sooner by naming the claim, the evidence, and the artifact it should produce.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria..
Example
Hermes operations proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the hermes operations pattern.
Example
Teach-back module
Transform the lesson into a definition, a Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
treating UI features as reliability
missing logs
no stop/recover path
Letting the lesson drift into feature cheerleading.
Letting the lesson drift into ops advice without logs/state.
Letting the lesson drift into assuming reliability from a demo alone.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This video argues that Hermes Agent is best used not as a replacement for Claude or Codex in building apps, but as an always-on operator/AI employee, and walks through 15 concrete business roles for it (SEO analyst, lead scraper, sales CRM, research agent, content producer, investment analyst, advisory council, etc.).
02
Explain the practical stakes without hype: New playlist item from Nemanja Mirkovic; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: 15 Hermes Agent use cases I wish I tried sooner
- URL: https://www.youtube.com/watch?v=gpJNLgv3vdw
- Topic: Creative Automation
- My current learning frame: Choose one time-draining bottleneck in your own work, then specify which part Claude/Codex should build as a tool and which part Hermes should operate on a cron, mirroring the build-vs-operate split the video demonstrates with the backlink CLI and portfolio tracker.
- Why this matters: New playlist item from Nemanja Mirkovic; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:12 / Evidence 1: "wanted Hermes Agent to replace those two so that they can build apps, build systems, build content inside of Hermes and not touch Claude or Codex anymore other than the models from them. And it absolutely can do..."
- 1:50 / Evidence 2: "them I use every day. And if you want more ideas, you can find a ton of them here on News Research website. And you can just browse and get ideas how people are using Hermes Agent. So,..."
- 3:24 / Evidence 3: "does LinkedIn. So, that's a really useful one if you do outbound. Sales CRM, in my previous video, I'm going to link it somewhere above, I used Hermes Agent to connect to my HighLevel CRM and to do..."
- 5:34 / Evidence 4: "and I sent it to my agent, and we worked out an idea for this video, how we can create this. So, it it adjusts the sources, and it creates the package or outline or scripts, whatever you..."
- 7:08 / Evidence 5: "CLI connected there, give it access, and it can create wonderful reports, and it can monitor things for you, and yeah, just figure out how you can give it access to things. Obviously, scope it so that you..."
- 9:12 / Evidence 6: "over. And yeah, it said that Microsoft is the best. I'm not going to argue with this. It's just one example how you can use this agent. It also has my portfolio tracker that I created with Cloud..."
- 10:56 / Evidence 7: "how this context works because Tony is in events. Personalized coaching. Yeah, and you can see sales call intelligence, obviously, we mentioned that. Offer optimization agent, great. Content repurposing, great, yeah. Customer proof flywheel. Yeah, absolutely. So, this..."
Video-aware target:
- Prompt lane: Hermes operations
- Mechanism to extract: Identify the operations control that makes long-running agent work visible, recoverable, or safer.
- Artifact to produce: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
- Artifact must include: health check; state model; permission boundary; log source; recovery action
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Identify the operations control that makes long-running agent work visible, recoverable, or safer. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review
- answers to these source questions: What operational failure is prevented? | What state is visible? | What can be recovered or redirected?
- 3 concrete examples that apply the video idea to real agentic work, such as Hermes Kanban triage; local model endpoint check; agent swarm recovery review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: treating UI features as reliability; missing logs; no stop/recover path
- a checklist for the next real workflow, focused on: status, model/backend, tools, logs, recovery
- one practical exercise with a clear done signal: Write a runbook for restarting one stuck Hermes-style agent session.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "15 Hermes Agent use cases I wish I tried sooner", not a generic Creative Automation essay.
- Ground each ops recommendation in transcript evidence about state, queues, models, tools, security, logs, or recovery.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: feature cheerleading; ops advice without logs/state; assuming reliability from a demo alone.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria..
A reusable artifact with a done signal and one verification step.03
Hermes operations teach-back card
Explain the hermes operations mechanism to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
What is the creator's core build-vs-operate split for Hermes, and what concrete example (the backlink tool) illustrates it?
What mechanism makes the daily research agent improve over time instead of staying static, and what does it replace?
How does the 'Warren' investment-analyst agent gather data and log trades, and what capability did its custom portfolio tracker have that off-the-shelf ones lacked?
Source shelf
Use the video as a doorway, then verify with primary sources.
