PAPER · PEER-REVIEWEDRLEE · VOL. LVI · NÚM. 2MAYO-AGOSTO 2026 · PP. 163-188

The teacher–AI dialogue: an analysis of interaction profiles with generative artificial intelligence

AuthorsMedina-Gual, L., Bazaldua-Huerta, D. F., Narváez-Serrano, L. R., & Degetau-Arsuaga, D.
PublicationRevista Latinoamericana de Estudios Educativos, LVI(2), 163–188
MethodsK-Means, PCA, expert panel validation
Corpus7,340 conversations · 22 educational institutions
§ 01 · ABSTRACT

The study in one page.

This study analyzed the nature of dialogue between teachers and Generative Artificial Intelligence in educational contexts, based on 7,340 anonymized conversations from the comenio.ai platform. An analytical framework was inductively developed and applied at scale using a large language model. Subsequently, K-means clustering and Principal Component Analysis (PCA) were employed to identify patterns of use. The results revealed three main profiles: Instrumental–Transactional (50.7%), oriented towards optimizing tasks and processes; Pedagogical Co-designer (29.2%), focused on generating complex learning experiences; and Reactive Repair Dialogue (20.1%), characterized by iterative interactions aimed at correcting AI limitations. The study provides an empirically grounded typology of teacher–AI dialogue, along with a conceptual and methodological framework to guide future research and the design of teacher professional development programs for the strategic use of generative AI tools in education.

Keywordsartificial intelligence · human–machine interaction · educational technology · basic education

§ 02 · INTRODUCTION

Dialogue, reloaded.

The arrival of generative artificial intelligence (GenAI) in the educational ecosystem is no longer hypothetical — it is a daily reality. From class planning to the creation of teaching materials, thousands of educators across Latin America interact every day with models like ChatGPT in a dialogical process with a non-human interlocutor.

This new dynamic transcends the mere adoption of a technological tool: it forces us to question the very nature of dialogue in education. Historically conceived as a pillar of collaborative knowledge construction and critical thinking, dialogue now faces a crossroads.

Can this interaction become a catalyst for a liberating education — or does it risk consolidating as an instrumental monologue that prizes efficiency over pedagogical reflection?

Dialogue as an object of study has evolved from a social practice into a rigorous multidisciplinary field. Its analysis has been characterized as a complex system articulated around four key components: structural elements regulating turns; participant dynamics, defining roles and power; intention, orienting conversation toward specific goals; and interactive features such as feedback and the repair of communicative breakdowns.

How teachers dialogue with AI is therefore a privileged window into their practice and professional agency. This study aims to characterize the nature of dialogue between teachers and GenAI: identifying frequent patterns in real conversations, establishing predominant use profiles via cluster analysis, and describing interaction constellations by purpose, nature and thematic domain.

METHODOLOGICAL PHASE
§ 03 · METHODOLOGY

Coding at scale.

To characterize teacher-chatbot dialogues we used a mixed-methods, predominantly quantitative, sequential exploratory design — combining expert validation, emergent qualitative analysis, and automated coding at scale. The process was articulated in two phases: developing a robust analytical framework, and applying it to the corpus.

Data & corpus

Data come from comenio.ai, a teacher-assistance platform with six chatbots. The sample was drawn from the chatbot focused on the New Mexican School (NEM) for basic education. The corpus comprised 7,340 complete, anonymized conversations stripped of any personal identifiers. The unit of analysis was the "complete conversation" — every exchange between a teacher and the AI from initial request to conclusion.

Phase 1 — Analytical framework

Rather than starting from a predefined framework, we used an iterative process. A multidisciplinary expert panel engaged in human-in-the-loop calibration: Gemini 2.5 Pro was used as a synthesis and conceptual probing tool, generating code-grouping proposals that experts then critically evaluated, refined and validated. Final categorical decisions always rested with the panel.

Phase 2 — Automated coding

Once validated, a Python tool used the OpenAI API (gpt-4o-2024-08-06) with Structured Outputs to strictly adhere to the defined Pydantic schema. The resulting dataset records the presence (True) or absence (False) of each code per conversation.

Analysis proceeded in four phases: (1) descriptive frequencies; (2) Phi (φ) correlation matrix; (3) profile identification with K-Means (K=3), grounded in the Elbow Method, Silhouette Coefficient and theoretical criteria; (4) dimensional reduction via PCA, complemented by discursive analysis of representative cases.

Fig. 02Representative cases for each profile — turns reconstructed from the corpus.

P1 · Instrumental2 turns · 14s
Teacher · t=0s
What are the articulating axes of the New Mexican School?
comenio · t=4s
The seven axes are: inclusion, critical thinking, critical interculturality, gender equality, healthy living, cultural appropriation through reading and writing, and arts & aesthetic experiences.
Conversation ends
Purposecontenido_basico
Typetransaccional
P2 · Codiseñador11 turns · 24m
Teacher · t=0s
I want a 5-session plan on «I am a boy or girl» for preschool.
comenio · t=11s
Plan v1 — sessions 1–5 with NEM goals, expected products and materials...
Teacher · t=2m
Rewrite session 2 so the child is the protagonist — not the teacher.
comenio · t=2m 18s
Plan v2 — child-led exploration, reduced teacher scaffolding...
Teacher · t=8m
Add a 4-level rubric and a closing field trip.
+ 6 turns
Purposeactividad_compleja
Typeiterativa_dialogica
P3 · Reparación7 turns · 18m
Teacher · t=0s
Plan for the «storm of perspectives» project.
comenio · t=8s · failure
Hmm, I'm not sure about that project. Could you give me more details?
Teacher · t=1m
It's from NEM, phase 3, curricular content.
comenio · t=1m 22s
Partial response — only includes 2 of the 7 axes...
Teacher · t=4m
Check again. You're missing the articulating axes.
+ 2 turns · failure persists
Bot failure53%
Typereparación
FINDINGS
§ 04 · RESULTS

A spectrum, not a monolith.

Descriptive analysis shows a clear tilt toward instrumental uses. basic_content_generation (57.3%) is the most prevalent category, and 54% of dialogues are classified as teaching-centered. But a notable interest in constructivist methods is also present: 46.6% are learning-centered, and 31.3% involve complex activity design.

Notably, metacognition about the AI itself is nearly absent (0.5%). In practical use, teachers treat the AI mainly as a functional "black box," with no visible interest in discussing its internal workings during interaction.

Purpose · what forn / 7,340
generacion_contenido_basico
57.3%
diseño_actividad_compleja
31.3%
adaptacion_personalizacion
22.0%
evaluacion_retroalimentacion
15.5%
desarrollo_proyecto_completo
9.2%
solicitud_integracion_curricular
8.2%
exploracion_conceptual_creativa
6.2%
Nature · hown / 7,340
interaccion_transaccional
60.2%
interaccion_iterativa_dialogica
39.8%
fallo_del_chatbot
31.0%
andamiaje_del_prompt
14.3%
solicitud_clarificacion_ia
6.0%
feedback_pedagogico_ia
5.8%
metacognicion_sobre_ia
0.5%
Pedagogical focusn / 7,340
contenido_curricular_especifico
80.2%
centrado_en_ensenanza
54.0%
centrado_en_aprendizaje
46.6%
planificacion_didactica_general
33.0%

Fig. 03Frequency of each code across the full corpus (n=7,340). The 19 framework dimensions, grouped by category.

Correlation analysis · φ matrix

The correlation map reveals a strong dichotomy: basic content generation is negatively correlated with complex activity design (φ = -0.51) and positively with teaching-centered focus (φ = 0.41). Conversely, complex activity design has its strongest positive correlation with learning-centered focus (φ = +0.60).

Regarding interaction nature, there is near-total mutual exclusion between transactional and dialogical interactions (φ = -0.87). Iterative dialogue is positively associated with personalization (φ = +0.50) and prompt scaffolding (φ = +0.43): longer dialogues are functionally tied to task sophistication, not chance.

gen_contenido_basico
diseño_actividad_cmplx
adaptacion_person
eval_retroalim
desarrollo_proy
centrado_ensenanza
centrado_aprendizaje
interaccion_transac
interaccion_dialog
andamiaje_prompt
fallo_chatbot
planif_didactica
contenido_curricular
gen_contenido_basico
-.51
-.18
-.10
-.20
+.41
-.30
+.36
-.36
-.22
+.08
-.05
+.04
diseño_actividad_cmplx
-.51
+.32
+.18
+.30
-.12
+.60
-.32
+.32
+.34
+.28
+.14
adaptacion_person
-.18
+.32
+.20
+.16
-.05
+.28
-.36
+.50
+.30
+.05
+.20
+.04
eval_retroalim
-.10
+.18
+.20
+.08
+.05
+.16
-.10
+.18
+.10
+.04
+.10
desarrollo_proy
-.20
+.30
+.16
+.08
-.05
+.32
-.18
+.20
+.18
+.22
+.08
centrado_ensenanza
+.41
-.12
-.05
+.05
-.05
-.40
+.34
-.30
-.08
+.04
+.08
+.10
centrado_aprendizaje
-.30
+.60
+.28
+.16
+.32
-.40
-.42
+.40
+.34
+.30
+.12
interaccion_transac
+.36
-.32
-.36
-.10
-.18
+.34
-.42
-.87
-.45
-.20
interaccion_dialog
-.36
+.32
+.50
+.18
+.20
-.30
+.40
-.87
+.43
+.06
+.24
+.04
andamiaje_prompt
-.22
+.34
+.30
+.10
+.18
-.08
+.34
-.45
+.43
+.05
+.18
+.04
fallo_chatbot
+.08
+.05
+.04
+.04
+.06
+.05
planif_didactica
-.05
+.28
+.20
+.10
+.22
+.08
+.30
-.20
+.24
+.18
+.18
contenido_curricular
+.04
+.14
+.04
+.08
+.10
+.12
+.04
+.04
+.18
φ = −1
+1

Fig. 04φ correlation matrix between the 13 most relevant codes. Red = negative correlation; blue = positive. The diagonal highlights the near-total exclusion between transactional and dialogical interaction (φ = −0.87).

PC1PC2σ² = 44.12% · n = 670Instrumental50.7%Codiseñador29.2%Reparación20.1%
Instrumental–Transaccional· 50.7%
Codiseñador Pedagógico· 29.2%
Reparación Reactiva· 20.1%

Fig. 05PCA: 19 dimensions reduced to two components — Pedagogical Sophistication (PC1) and Dialogue Elaboration (PC2). Variance explained: 44.12%.

VariableInstrumental–Trans.Codiseñador Ped.Reparación reactiva
generacion_contenido_basico0.700.150.86
diseño_actividad_compleja0.040.930.10
solicitud_integracion_curricular0.020.280.06
desarrollo_proyecto_completo0.000.300.01
adaptacion_personalizacion0.070.620.19
evaluacion_retroalimentacion0.070.280.20
exploracion_conceptual_creativa0.020.130.11
centrado_en_ensenanza0.660.310.57
centrado_en_aprendizaje0.160.970.51
interaccion_transaccional0.970.350.00
interaccion_iterativa_dialogica0.000.520.96
andamiaje_del_prompt0.000.400.17
solicitud_clarificacion_ia0.030.060.12
feedback_pedagogico_ia0.060.060.05
fallo_del_chatbot0.290.200.53
contenido_curricular_especifico0.740.920.77
planificacion_didactica_general0.150.680.32
metacognicion_sobre_ia0.010.000.01

Tabla 01Centroids of the three clusters across the 18 framework variables. Background intensity encodes each variable's prevalence within the profile.

§ 05 · THE THREE PROFILES

Instrumental, Co-designer & Repair.

50.7%
● CLUSTER 01

Instrumental–Transactional

Short, direct requests. AI as a productivity assistant: factual content, lists, definitions.

interaccion_transaccional97%
generacion_contenido_basico70%
centrado_en_ensenanza66%
29.2%
● CLUSTER 02

Pedagogical Co-designer

Collaborative design of learning experiences. Adaptation, scaffolding and multi-phase projects.

diseño_actividad_compleja93%
centrado_en_aprendizaje97%
adaptacion_personalizacion62%
20.1%
● CLUSTER 00

Reactive Repair

Iterations to repair bot failures. Extended dialogue by necessity, not by strategy.

interaccion_iterativa_dialogica96%
fallo_del_chatbot53%
generacion_contenido_basico86%

Fig. 01Three emergent teacher-use profiles identified via K-Means (K=3) over 7,340 conversations. Bar length shows code prevalence within each cluster.

DISCUSSION
§ 06 · DISCUSSION

Three ways of being-with AI.

Results reveal that teacher–AI dialogue is not monolithic but a spectrum oscillating between instrumental efficiency and complex pedagogical co-creation. The identification of three profiles does not merely quantify patterns; it offers a lens to interpret the tensions, challenges and opportunities GenAI introduces into teaching practice.

More than half of the corpus concentrates in the Instrumental mode — AI, first, is a productivity assistant.

The prevalence of the Instrumental–Transactional profile — over half of interactions — confirms that AI is adopted first as a productivity assistant. While this answers a real need to optimize tasks, it raises a pedagogical risk: from a Freirean critical reading, this pattern can be interpreted as a form of "banking education" where the AI becomes a new repository of knowledge from which the teacher simply extracts resources.

The Pedagogical Co-designer profile, by contrast, demonstrates the tool's transformative potential. Nearly a third of teachers use AI not to answer questions but to think with it — co-constructing learning experiences, adapting content, scaffolding entire projects. This profile embodies what we might call the "augmented teacher."

The third profile, Reactive Repair, is perhaps the most revealing about the technology's current state. Its iterativity is not strategic but reactive: a fifth of all interactions occur because the system failed and the teacher persisted. This evidences both the technical limitations of current chatbots and the professional agency of teachers who refuse to accept the first inadequate answer.

CONCLUSIONS
§ 07 · CONCLUSIONS

From users to designers.

This study characterized teacher–AI dialogue and identified a spectrum of practices from instrumental consultation to complex co-creation. The three profiles offer both a snapshot of the current state and a conceptual framework for understanding its pedagogical implications — highlighting that AI mirrors the teacher's intentionality and agency: the quality of the pedagogical product depends on the quality of the dialogue conducted.

From users to interaction designers: AI literacy as a new teacher competence.

Teachers may shift from a role of "users" to one of "interaction designers," developing AI-literacy skills such as prompt engineering. One path forward is the formation of communities of practice to share strategies, alongside developers building pedagogically informed chatbots capable of understanding teacher intent and supporting the repair of communicative breakdowns.

Methodologically, the paper contributes a validated, scalable analytical framework useful for research, AI tool design and teacher formative assessment. The resulting typology can guide professional development toward the Pedagogical Co-designer profile.

§ 08 · HOW TO CITE

APA reference.

APA · 7TH ED.

Medina-Gual, L., Bazaldua-Huerta, D. F., Narváez-Serrano, L. R., & Degetau-Arsuaga, D. (2026). El diálogo docente–IA: análisis de los perfiles de interacción con inteligencia artificial generativa. Revista Latinoamericana de Estudios Educativos, LVI(2), 163–188. https://doi.org/10.48102/rlee.2026.56.2.798