What this rubric measures
The AP Seminar PT1 Team Project Rubric is the official scoring guide used to evaluate student writing on AP Seminar assessments. It is an Analytic (11 rows across two artifacts) rubric that scores responses across 11 distinct criteria, allowing teachers to give precise, targeted feedback on each area of writing.
All 11 scoring criteria
Click any criterion to expand its score level descriptors. The language below is taken verbatim from the official College Board AP Seminar scoring guide.
1 IRR Row 1: Understand and Analyze Context
The report situates the student's investigation of the complexities of a problem or issue in research that draws upon a wide variety of appropriate sources. It makes clear the significance to a larger context. Responses earning 6 points:
- Clearly state an area of investigation that is narrow enough to address the complexity of the problem or issue. The context established is sustained throughout.
- Predominantly include research sources appropriate for an academic task on this topic.
- Provide specific and relevant details to convey why the problem or issue matters/is important.
The report identifies an adequately focused area of investigation in the research and shows some variety in source selection. It makes some reference to the overall problem or issue. Responses earning 4 points:
- Identify too many aspects of the topic to address complexity.
- May be overly reliant on research sources not appropriate for an academic task on this topic.
- May provide a rationale about the significance of the investigation that lacks details necessary to address complexity.
The report identifies an overly broad or simplistic area of investigation and/or shows little evidence of research. A simplistic connection or no connection is made to the overall problem or issue. Responses earning 2 points:
- Address a very general topic of investigation.
- Draw mainly from one or two sources or poor-quality sources.
- Provide an overly simplistic, illogical, or exaggerated rationale for the investigation (or does not provide a rationale at all).
Does not meet the criteria for two points. Responses that earn 0 points:
- Provide no evidence of research (i.e., complete absence of bibliography, internal citations, and attributive tags).
IRR Row 1 scores how well the report situates the investigation within a relevant context using a wide variety of appropriate sources. The research context is often in titles and first paragraphs, but the whole report must sustain the focus throughout.
2 IRR Row 2: Understand and Analyze Argument
The report demonstrates an understanding of the reasoning and validity of the sources' arguments. This can be evidenced by direct explanation or through purposeful use of the reasoning and conclusions. Responses earning 6 points:
- Provide commentary that explains authors' reasoning, claims or conclusions (direct explanation).
- Make effective use of authors' reasoning, claims or conclusions (showing understanding of the sources) (purposeful use).
- Attribute clearly source material (i.e., readers always able to tell what comes from what source).
The report summarizes information and in places offers effective explanation of the reasoning within the sources' argument (but does so inconsistently). Responses earning 4 points:
- Are dominated by summary of source material rather than explanation of sources' arguments.
- Provide some instances of effective explanation of authors' reasoning.
- Occasionally lack clarity about what is commentary and what is from the source material.
The report restates or misstates information from sources. It doesn't address reasoning in the sources or it does so in a very simplistic way. Responses earning 2 points:
- Make no distinction between paraphrased material and response's commentary.
- Demonstrate no instances of effective explanation. Commentary is limited to restatement of quotes, is simplistic or overgeneralized, or shows misunderstanding of the source.
- Do not anchor ideas to sources (or does so generally, "research shows" or "some studies").
Does not meet the criteria for two points. Responses that earn 0 points:
- Provide no evidence of research (complete absence of bibliography, citations, and attributive tags).
IRR Row 2 scores the student's understanding of the reasoning and validity of the sources' arguments. Reference to source arguments often appears at the end of paragraphs and/or immediately following an in-text citation.
3 IRR Row 3: Evaluate Sources and Evidence
The report demonstrates evaluation of credibility of the sources and selection of relevant evidence from the sources. Both can be evidenced by direct explanation or through purposeful use. Responses earning 6 points:
- Provide descriptions in the attributions that effectively establish credibility of the source and relevance of evidence (direct explanation).
- Make effective use of well-chosen, relevant evidence from credible academic sources (purposeful use).
The report in places offers some effective explanation of the chosen sources and evidence in terms of their credibility and relevance to the inquiry (but does so inconsistently). Responses earning 4 points:
- Contain attributions or explanations for non-academic sources that do not successfully establish credibility.
- Pay attention to the evidence, but not the source (may treat all evidence as equal when it is not).
- Draw upon outdated research without providing a rationale for using that older evidence.
The report identifies evidence from chosen sources. It makes very simplistic, illogical, or no reference to the credibility of sources and evidence, and their relevance to the inquiry. Responses earning 2 points:
- Provide evidence that is poorly selected in terms of relevance and credibility.
- Provide evidence without addressing relevance and credibility.
- Demonstrate consistent lack of understanding of selected evidence.
- May include credible sources, but oversimplify or reduce them to generalities.
Does not meet the criteria for two points. Responses that earn 0 points:
- Provide no evidence of research.
IRR Row 3 scores evaluation of source credibility and selection of relevant evidence. Purposeful use refers to the deployment of relevant evidence from a credible source. Clear attribution must be present for purposeful use.
4 IRR Row 4: Understand and Analyze Perspective
The report discusses a range of perspectives and draws explicit and relevant connections among those perspectives. Responses earning 6 points:
- Go beyond mere identification of multiple perspectives by using details from different sources' arguments to explain specific relationships or connections among perspectives (i.e., placing them in dialogue).
The report identifies multiple perspectives from sources, making some general connections among those perspectives. Responses earning 4 points:
- Include multiple perspectives and some instances of general connections.
- Repeat perspectives or connections rather than developing a nuanced, detailed discussion of how they relate.
- At times present perspectives that are clearly derived from specific sources, but may lapse into opinions or topics that are not clearly linked to specific sources.
The report identifies few and/or oversimplified perspectives from sources. Responses earning 2 points:
- May include oversimplified or vaguely attributed perspectives (it is unclear whether or not they are from sources).
- May identify information from sources (facts or topics or general stakeholder point of view) but not points of view as conveyed through arguments.
- Juxtapose perspectives but connections are not clear (they are isolated from each other).
Does not meet the criteria for two points.
- Provide no evidence of research.
IRR Row 4 scores the discussion of perspectives. A perspective is "a point of view conveyed through an argument" (the source's argument). Facts, topics, and general stakeholder points of view are not perspectives. Scoring note: clear attribution must consistently link perspectives to sources to score high.
5 IRR Row 5: Apply Conventions (Citation)
The report attributes and accurately cites the sources used. The bibliography accurately references sources using a consistent style. Responses earning 3 points:
- Contain few flaws.
- Provide clear organization principle in bibliography/works cited.
- Provide consistent evidence of linking internal citations to bibliographic references.
- Include consistent and clear attributive phrasing for paraphrased material and/or in-text parenthetical citations.
The report attributes or cites sources used but not always accurately. The bibliography references sources using a consistent style. Responses earning 2 points:
- Provide some uniformity in citation style.
- Provide, perhaps with a few lapses, an organizational principle in bibliography/works cited.
- Include unclear references or errors in citations (e.g., citations with missing elements).
- Provide some successful linking of citations to bibliographic references.
The report includes many errors in attribution and citation OR the bibliography is inconsistent in style and format and/or incomplete. Responses earning 1 point:
- Include internal citations, but no bibliography (or vice versa).
- Demonstrate no organizational principle in bibliography/works cited.
- Provide little or no evidence of successful linking of in-text citations to bibliographic references.
- Include poor or no attributive phrasing with paraphrased material (e.g., "Studies show..." with no in-text citation).
Does not meet the criteria for one point.
- Provide no evidence of research.
IRR Row 5 scores citation conventions. No particular style sheet is required in AP Seminar, but the response must use a style that is consistent and complete. Cannot score 3 if essential elements (author/organization, title, publication, date) are consistently missing.
6 IRR Row 6: Apply Conventions (Style)
The report communicates clearly to the reader (although may not be free of errors in grammar and style). The written style is consistently appropriate for an academic audience. Responses earning 3 points:
- Contain few flaws which do not impede clarity for understanding of complex ideas.
- Demonstrate word choice sufficient to communicate complex ideas.
- Use clear prose.
The report is generally clear but contains some flaws in grammar that occasionally interfere with communication to the reader. The written style is inconsistent and not always appropriate for an academic audience. Responses earning 2 points:
- Contain some lapses in sentence control (e.g., run-ons, fragments, or mixed construction when integrating quoted material).
- Demonstrate imprecise or vague word choice insufficient to communicate complexity of ideas.
- Sometimes lapse into colloquial language.
- Use overly dense prose at the expense of coherence and clarity.
The report contains many flaws in grammar that often interfere with communication to the reader. The written style is not appropriate for an academic audience. Responses earning 1 point:
- May contain many instances where sentences are not controlled.
- May rely almost exclusively on simplistic language.
- Employ an overall style that is not appropriate for an academic report; or colloquial tone.
- Include many passages that are incoherent.
Does not meet the criteria for one point.
- Contain no sentences created by the student.
IRR Row 6 scores grammar and academic style. Because the IRR is a report, the prose is judged by its ability to clearly and precisely articulate complex research content. Readers should focus on the sentences written by the student, not those quoted or derived from sources.
7 TMP Row 1: Establish Argument
The presentation conveys the convincing argument for the team's solution or resolution through strategic selection of supporting evidence. Responses earning 6 points:
- Present a clear, coherent, and complex argument for the team solution.
- Make the logic of the argument clear through strategic selection of key claims and relevant supporting evidence.
- Contain only relevant material sufficient to successfully make the argument within the given time limit.
- Present a viable and convincing solution that is tightly connected to the argument and illustrates the complexity of the issue.
- Demonstrate mostly consistent, logical connection among speakers.
The presentation conveys the argument for the team's solution or resolution using evidence that is not well selected for the situation. Responses earning 4 points:
- Present a clear and coherent argument for a team solution but only some claims are supported by evidence.
- Demonstrate selection and emphasis that are not always controlling: at times may have instances of extraneous information or too much for time limit.
- Offer a solution that has some logical connection to the problem, but it is weak (for example, overgeneralized, oversimplified).
- Demonstrate only some logical connection among speakers.
The presentation describes the existence of a problem or reports on a problem, but does not argue for a team solution or resolution. Responses earning 2 points:
- Provide only individual solutions rather than a team solution.
- Present individual reports yoked by a very broad theme or offer evidence related to a topic (rather than an argument).
- Identify a team solution that is not explained, justified, or supported.
- Argue for the existence of a problem with a solution tagged on at the very end.
The presentation offers a series of unsubstantiated opinions. It is not academic in nature.
TMP Row 1 scores how convincingly the team's argument is presented. Only the first 10 minutes of any presentation are scored (excluding the oral defense).
8 TMP Row 2: Understand and Analyze Context (Evaluate Solutions)
The presentation explains the pros and/or cons of potential options and situates the team's proposed solution in conversation with them. AND The presentation evaluates the solution proposed by the team by thoroughly explaining its limitations or implications. Responses earning 4 points:
- Fully meet both rubric criteria.
The presentation describes pros and/or cons of potential options related to the topic. OR The presentation describes limitations or implications of the solution proposed by the team, but in an inconsistent, illogical, overly broad, or otherwise unconvincing manner. Responses earning 2 points:
- Meet one of the rubric criteria or partially meet both criteria.
The presentation does not identify or only minimally identifies solutions, either the team's or others' (e.g., a list of solutions with brief annotations).
TMP Row 2 scores how well the team situates its solution in relation to other potential options AND evaluates limitations/implications. Increments by 2 (0, 2, 4).
9 TMP Row 3: Engage Audience (Performance)
All presenters effectively engage the audience through strategic intentional use of performance techniques most of the time. Responses earning 6 points:
- Have all presenters use strategies to effectively engage the audience (most of the time).
At times, some presenters (i.e. more than one) effectively engage the audience. As a team the presenters demonstrate uneven delivery or performance techniques. Responses earning 4 points:
- Have at least two presenters use strategies to effectively engage the audience at least some of the time (but others don't).
All or all but one of the presenters make little or no use of techniques to engage the audience. Responses earning 2 points:
- Have only one presenter that uses strategies to effectively engage the audience.
- Have no presenters that use strategies to effectively engage the audience.
The presenting is entirely inappropriate for the audience, purpose or context.
TMP Row 3 scores delivery and performance techniques. There may be minor lapses at the 6-point level, but they do not detract from the overall impression of an engaging presentation.
10 TMP Row 4: Engage Audience (Design)
Overall, the design clearly guides viewers through the presentation and demonstrates strategic selection of media and design elements that help clarify the argument for the team's solution. Responses earning 4 points:
- Provide visuals that overall serve a clear purpose in organizing or advancing the team argument (such as clear and logical signposting).
- Include well-chosen words and images throughout to highlight key points or information.
- Present visuals that contain little clutter or visual "noise"; they enhance rather than compete with the speaker's message.
- Create cohesion through consistency of design across the team throughout.
The presentation's design demonstrates an understanding of media and design elements but does not enhance the team's message, or does so inconsistently. Responses earning 2 points:
- Provide visuals that guide the audience through topics in a presentation but are at times ineffective in terms of advancing a team argument.
- Include several visuals that display information overload or a poor selection of supporting words and images.
- May include visuals that contain some noticeable, significant errors.
- Demonstrate inconsistent visual and design cohesion across the team.
The presentation demonstrates no design or minimal design with significant errors.
- Provide no signposting to guide the audience through the presentation.
- Provide visuals that may be little more than blocks of pasted information or informal notes.
- Demonstrate no principle of visual design across speakers.
TMP Row 4 scores visual design. Increments by 2 (0, 2, 4). The team's visual cohesion across speakers is part of the scoring criteria.
11 TMP Row 5: Collaborate and Reflect (Oral Defense)
All responses in the oral defense articulate detailed answers to the question asked and support those answers with relevant evidence specific to collaboration on this project. AND The answers in the oral defense taken together with the presentation demonstrate roughly equal participation from all team members. Responses earning 4 points have all team members responding at the High level:
- Fully answer the question asked.
- Provide detailed evidence from team project sufficient to support their answer.
- Demonstrate accurate knowledge/understanding of teammates' work or the team's argument.
Two or more of the responses in the oral defense support their answers with some relevant evidence specific to the team's project. Responses earning 2 points have at least two team members responding at the Medium level:
- At least partially answer the question asked.
- Have some evidence from the team project but may lack elaboration or detail.
- Demonstrate some limited knowledge/understanding of teammates' work or the team's argument.
All or all but one member of the team offer generic responses that could apply to any collaborative project. Or the answers by all or all but one of the team may be unacceptably brief. Responses earning 0 points have all (or all but one) team members responding at the Low level:
- Don't answer the question asked (even partially).
- Are generic (it could be about any project).
- Are very brief.
- Demonstrate a lack of understanding of the team's project.
TMP Row 5 scores the team oral defense. Each individual response must be evaluated as low, medium, or high. All high = 4 points; at least two medium = 2 points; all or all but one low = 0 points.
How to score with the AP Seminar PT1 Team Project Rubric.
A practical guide for teachers and norming teams. How to apply each descriptor consistently, the pitfalls that hurt inter-rater reliability, and a workflow for calibrating with colleagues.
Two artifacts, scored separately
- PT1 has two scored artifacts. The Individual Research Report (IRR) is 30 points across 6 rows. The Team Multimedia Presentation (TMP) is 24 points across 5 rows.
- The IRR is scored individually for each team member. The TMP is scored once for the team as a whole.
- Total PT1 score per student combines that student's IRR score with the team's TMP score for a maximum of 54 points.
Time and scope rules
- Only the first 10 minutes of the team presentation are scored. The oral defense is scored separately and does not affect Rows 1 through 4 of the TMP.
- The IRR is typically 1,200 words. The TMP runs longer than 10 minutes with the oral defense, but only the first 10 minutes of the presentation proper are scored.
- Each row is scored against the preponderance-of-evidence (best-fit) standard, applied to the artifact independently.
Common pitfalls to avoid
- Awarding IRR Row 4 (Perspectives) 6 points for identifying multiple stakeholder views without using those views as ARGUMENTS in dialogue with one another.
- Awarding TMP Row 1 (Argument) 6 points for a presentation that reports on a problem with a solution tagged on at the end.
- Awarding TMP Row 5 (Oral Defense) 4 points without checking that all team members are responding at the High level, individual low responses prevent the team from earning 4.
- Awarding IRR Row 5 (Citation) 3 points when essential elements (author, title, publication, date) are consistently missing.
Tips for AP norming
- Anchor your norming session with the College Board's released sample IRRs and TMP recordings.
- IRR Row 4 (Perspectives) and IRR Row 2 (Sources' Argument) are the highest-variance rows. Norming requires distinguishing source-argument-as-perspective from source-information-as-fact.
- For the TMP oral defense (Row 5), score each individual response BEFORE assigning a team score. The all-high/two-medium/two-low rule is mechanical once individuals are rated.
Notes for the AP Seminar PT1 Team Project Rubric
Performance Task 1 is the year-long AP Seminar team project. Teams of 3 to 5 students choose a real-world problem or academic issue, divide research, and build both individual research reports and a team multimedia presentation. Total possible is 54 points across 11 scored rows.
The Individual Research Report (IRR) is scored individually for each team member across 6 rows. The Team Multimedia Presentation (TMP) is scored once for the team across 5 rows, including an oral defense where each team member is independently rated low/medium/high.
The most common pattern of point loss on the IRR is on Row 4 (Perspectives). Students often present multiple stakeholder viewpoints as facts or topics rather than as argued perspectives drawn from sources. The 6-point level requires placing the perspectives "in dialogue" with one another using details from each source's argument.
The most common pattern of point loss on the TMP is on Row 1 (Establish Argument). Teams often present individual research summaries instead of a unified team argument with a defended solution. Strong 6-point TMPs identify a single team thesis early and have every team member's section explicitly support that thesis.
See this rubric in action.
EnlightenAI scores student writing on this exact rubric, with per-criterion feedback that mirrors how you grade by hand. The sample response below shows how the rubric applies to a real piece of student writing, scored against every criterion.
PT1 sample IRR excerpt on AI-assisted writing tools and equity of access
IRR introduction (verbatim excerpt)
Recent advances in large language models have changed what is possible for student writing in US public schools. While much of the public attention has focused on academic integrity, the equity-of-access dimension of these tools has received less sustained research treatment. This paper investigates how US public school districts should respond to the unequal availability of AI-assisted writing tools across student populations. The investigation draws on three lines of academic work: educational technology adoption research (Selwyn 2022; Williamson 2023), Title I funding equity analyses (Reardon 2019; Owens 2020), and recent peer-reviewed studies of AI tool use in K-12 contexts (Holstein and Aleven 2023; Chen et al. 2024).
IRR body (verbatim excerpt)
Selwyn (2022) argues that educational technology adoption tends to follow socioeconomic gradients, with higher-resource districts integrating new tools faster and with more pedagogical support. The pattern is empirically documented for tools ranging from calculators to interactive whiteboards. Williamson's (2023) complementary work emphasizes that the adoption gap is not just access but quality of integration, lower-resource schools tend to adopt new tools as labor-saving devices for teachers, while higher-resource schools adopt them as instructional partners. These two perspectives, taken together, predict that AI writing tools will widen rather than narrow existing achievement gaps unless districts intentionally counteract the pattern.
IRR perspectives section (verbatim excerpt)
A different perspective emerges from the work of Holstein and Aleven (2023). Their argument is that AI-assisted writing tools, properly deployed, can serve as personalized writing tutors for students whose home environments do not include adults available to coach writing. From this perspective, the equity case for AI tools is positive, lower-resource students stand to benefit more, not less, IF districts invest in deployment. Holstein and Aleven's argument places them in tension with Selwyn (2022) and Williamson (2023), who would respond that the IF clause is doing all the work and that historical patterns of district investment make it unlikely. The dialogue between these perspectives sharpens the policy question: are AI writing tools a force multiplier for existing inequality (Selwyn, Williamson), or a corrective lever IF districts invest deliberately (Holstein and Aleven)?
Strong contextual framing; some source-argument analysis underdeveloped
Row 1 earns 6 (narrow research focus, varied academic sources, clear significance to larger context). Row 2 earns 4, the report demonstrates understanding of source arguments in places but is dominated by summary in the body paragraphs. Combined Rows 1 and 2 earn 10 of 12.
Perspectives placed in dialogue; credibility uneven across sources
Row 4 earns 6 (Selwyn/Williamson placed in dialogue with Holstein/Aleven through explicit comparison of arguments). Row 3 earns 4 because credibility explanations are present for academic sources but absent for one non-academic citation. Combined Rows 3 and 4 earn 10 of 12.
Consistent citation style and clear academic prose
Row 5 earns 3 (clear organizational principle in works cited, consistent attributive phrasing). Row 6 earns 3 (clear prose with word choice sufficient for complex ideas). Combined Rows 5 and 6 earn 6 of 6.
Score this rubric consistently, with the feedback students actually use
EnlightenAI is trained on your standards and your exemplars, then scores at the speed of your classroom.
Trained on your rubric
Upload this rubric, or any custom one, and the AI learns your exact criteria, descriptor language, and score level boundaries.
Per-criterion feedback
Students receive specific, actionable comments tied to each criterion, exactly the way you'd grade by hand.
Built for K–12 schools
Roster sync, FERPA-aligned data handling, and per-school configuration so every campus uses the same standards.
About the AP Seminar PT1 Team Project Rubric
How is AP Seminar Performance Task 1 scored?
How long is the AP Seminar Team Multimedia Presentation?
How is the oral defense scored?
What is the IRR?
Is the IRR scored by my teacher or by the College Board?
Is this rubric the official version from College Board?
Where can I find the source document?
Can EnlightenAI score student writing using this rubric?
Use this rubric in EnlightenAI
Train EnlightenAI on the AP Seminar PT1 rubrics and start scoring student IRR drafts with consistent per-row feedback in a single class period.