Quick answer
The starting point was concrete: a marketing agency wanted to make better use of AI for quotes, schedules, reports and other professional tasks. Nord Paradigm prepared a Claude 101 workshop around the team’s questions, with a resource space and ten prompts to reuse in day-to-day work.
This case documents the preparation, materials and resources. It does not measure time saved or adoption after the session.
The starting point: everyday friction
The team already used AI tools. It wanted to put them to better use: preparing schedules from quotes, structuring campaign reports and avoiding the need to rebuild the same documents for each engagement.
The frustrations were specific. Generic responses. Sources that needed checking. An assistant that agreed instead of questioning an idea. Every experiment came with the same requirement: keep control over the quality of work delivered to clients.
Before the session, the agency collected its questions in a questionnaire. Strategy, project management, content, video and design were all represented. That document became the starting material for the workshop.
Turning questions into useful exercises
Nord Paradigm prepared Claude 101 around two areas: configuring the assistant for each person’s work and building reusable prompts for recurring tasks.
The session plan included a comparison before and after adding custom instructions, followed by building a prompt around a chosen task and examples. The method called for defining the deliverable, constraints and quality criteria before writing the instructions.
The prepared resources also addressed specific professional tasks: schedules, report analysis, SRT subtitles and After Effects expressions. Fictional files supported the planned demonstrations. This plan is not a record of which exercises each person completed.
A quote defines the engagement. The work still needs a schedule.
The questionnaire asked for a way to produce a project schedule from a quote and kickoff information. The corresponding resource first asks for the start date, milestones, dependencies and periods to avoid.
It then requests a table connecting phases with tasks, deliverables, owners and required approvals. A weekly view of workload by role completes the request. The project owner remains responsible for checking whether the schedule is realistic.
A report needs to separate what is known from what is assumed
For campaign reports, the team wanted to separate facts, hypotheses and recommendations. The prepared prompt follows that distinction: tie facts to the data, label possible explanations as hypotheses and identify missing information before recommending an action.
The structure makes review more precise. It does not replace missing data or the responsible person’s judgment.
Resources that remain available after the session
The prepared space contains ten prompts to copy and adapt. It covers custom instructions, prompt building, report analysis, schedules, files, interactive artifacts and video.
The prompt-building method begins with the task and its usual inputs. It then asks for appropriate examples, an expected deliverable and quality criteria, followed by a small test on fictional input. That gives the team a starting point for adapting the approach to other engagements.
The resources also address personal information, approved work environments and human review before delivery. For file operations, the prepared demonstration requires a renaming plan and agreement before making changes.
What this case demonstrates
The documented output is concrete: a workshop prepared around the team’s stated needs, demonstration materials and a prompt library tailored to agency work.
We have no measurement of time saved, adoption rates or commercial results to attribute to the session. Those questions would require a separate follow-up. Another team can still reuse the approach: collect the tasks, define the expected deliverables and prepare resources people can use in their work.
For more on the teaching approach, read from AI demo to working session. To prepare a workshop around a quote, report or another recurring task, discuss your team’s work with us.
Sources and limits of this case
The agency remains anonymous. The reported needs come from the questionnaire and preparation documents. The resource space contains the ten prompts and synthetic files prepared as teaching materials. The excerpts presented here make the method available for examination without exposing information about the agency or its clients.
The quote and report examples are fictional. Prepared materials do not establish that every exercise was completed or that the practices were adopted afterwards.
